Best way to make more money from Uber

If you're looking to make the most money possible driving for Uber, here are a few tips:

1. Drive during peak hours: The busiest times for Uber are typically during the morning and evening rush hours, as well as on weekends. By driving during these times, you'll have more opportunities to pick up passengers and earn money.

2. Know your city: Familiarize yourself with the most popular destinations in your city so you can anticipate where passengers are likely to need rides. You can also use the Uber driver app to see where other drivers are located and adjust your strategy accordingly.

3. Keep your car clean and well-maintained: Passengers are more likely to leave positive reviews and tip you if your car is clean and comfortable. Make sure you keep up with regular maintenance like oil changes and tire rotations as well.

4. Be polite and professional: Customer service is key when driving for Uber. Be friendly and courteous to passengers, and make sure you follow all traffic laws and safety guidelines.

5. Consider offering additional services: Some Uber drivers offer additional services like providing water or snacks for passengers, or even playing music or providing a phone charger. These small touches can help increase your ratings and earn you more tips.

Remember, driving for Uber can be a flexible and lucrative way to earn money, but it's important to put in the effort to maximize your earnings.

Best time to drive

The best time to drive for Uber can vary depending on your location, but generally, the busiest times are during the morning and evening rush hours, as well as on weekends and holidays. During weekdays, the busiest times are typically between 7-9 AM and 4-7 PM when people are commuting to and from work. On weekends, the busiest times are usually Friday and Saturday nights, as well as Sunday mornings and afternoons.

It's also worth noting that big events in your area, such as concerts or sporting events, can also be busy times for Uber drivers. You can check your driver app to see if there are any special events happening in your area, and plan your driving schedule accordingly.

Ultimately, the best time to drive for Uber is when there is high demand for rides and fewer drivers available to meet that demand. By keeping an eye on your driver app and staying up-to-date on local events and traffic patterns, you can maximize your earnings as an Uber driver.

What is uber alogarizim to make peack hours ?

Uber uses a dynamic pricing algorithm called "surge pricing" to incentivize more drivers to be on the road during busy times. When there is high demand for rides in a particular area, Uber will increase the fare rates for passengers to encourage more drivers to go to that area and pick up passengers. This surge pricing algorithm is designed to balance the supply and demand of drivers on the road, and ultimately provide better service to passengers.

Surge pricing can be triggered by a number of factors, including time of day, day of the week, and the availability of drivers in the area. Uber may also use other data sources to predict when demand for rides will be high, such as local events or weather patterns.

As a driver, surge pricing can be a great opportunity to earn more money, as you'll receive a higher fare for each ride you complete during a surge period. However, it's important to keep in mind that surge pricing can also lead to more competition among drivers, so it's important to stay informed and be strategic about when and where you choose to drive.

Uber surge pricing is a dynamic pricing algorithm that can vary based on a number of factors. Here are some of the variables that can impact surge pricing:

1. Time of day: Uber's surge pricing algorithm takes into account the time of day, as certain hours tend to be busier than others. For example, rush hour periods in the morning and evening may have higher surge pricing.

2. Day of the week: Certain days of the week tend to have higher demand for rides, such as Friday and Saturday nights, and surge pricing may be higher on these days.

3. Special events: Uber may also implement surge pricing during special events in a particular area, such as concerts, festivals, or sporting events.

4. Weather: In areas with inclement weather, surge pricing may increase as more people opt for ride-sharing services instead of driving themselves.

5. Supply and demand: Surge pricing is ultimately determined by supply and demand. If there are more riders than drivers available in a particular area, surge pricing will be higher.

It's important to note that surge pricing can vary greatly depending on the specific circumstances, and it's not always easy to predict when and where surge pricing will occur. As a driver, it's important to pay attention to your driver app and be strategic about when and where you choose to drive to take advantage of surge pricing opportunities.

The top 10 cities where Uber drivers can make the most money can vary depending on a number of factors, such as the cost of living in the area, the level of demand for rides, and local regulations. However, based on recent data and driver feedback, here are 10 cities where Uber drivers may be able to earn higher fares and more tips:

1. San Francisco, CA
2. New York City, NY
3. Boston, MA
4. Chicago, IL
5. Washington D.C.
6. Los Angeles, CA
7. Seattle, WA
8. Miami, FL
9. Dallas, TX
10. Philadelphia, PA

It's worth noting that these cities may also have higher competition among drivers, which could impact earnings. As a driver, it's important to be strategic about when and where you choose to drive in order to maximize your earnings potential.

The net income of an Uber driver can vary widely depending on a number of factors, such as the driver's location, the number of hours worked, and the driver's expenses. According to a study conducted by Ridester in 2021, the average Uber driver in the United States makes around $19 per hour before expenses.

Assuming an average of 30 hours worked per week, this would equate to a weekly income of $570 before expenses, or an annual income of $29,640. However, it's important to note that this figure can vary significantly depending on the driver's location and expenses, as well as fluctuations in demand and surge pricing.

It's also important to consider that as an independent contractor, Uber drivers are responsible for their own expenses, such as gas, car maintenance, and insurance. These expenses can add up quickly and significantly impact the driver's net income. As a result, it's important for drivers to carefully track their expenses and factor them into their earnings calculations.

What is the % Uber takes from each driver ?

The percentage Uber takes from each driver varies depending on the type of ride and the market. Generally, Uber takes a percentage of the fare as its commission or service fee. According to Uber's website, in the United States, Uber's service fee is typically 25% of the fare for UberX and UberPOOL trips, and 28% for UberBLACK, UberSUV, and UberLUX trips.

It's worth noting that in some markets or during certain promotions, Uber may take a higher or lower percentage as its commission. Additionally, Uber may take a different percentage for certain types of rides or for drivers with different levels of experience or ratings.

As an Uber driver, it's important to carefully review the terms and conditions of your contract with Uber and understand how the company calculates its commission or service fee. This information can help you to better manage your expenses and earnings as an independent contractor.

Uber's commission or service fee can vary from driver to driver and from market to market based on a number of factors. These factors may include the type of ride, the level of demand in a particular area, and the driver's experience or rating.

For example, Uber may offer lower commission rates to drivers who have completed a certain number of trips or have a higher driver rating. This can incentivize drivers to provide high-quality service and maintain a good reputation on the platform.

Additionally, Uber may adjust its commission rates based on supply and demand. During times of high demand, such as rush hour or special events, Uber may increase its commission to incentivize more drivers to come online and meet the increased demand for rides.

Overall, Uber's commission rates are determined by a complex algorithm that takes into account a number of factors, and can vary based on the specific circumstances of each ride and driver. It's important for drivers to carefully review their contracts with Uber and understand how their earnings are calculated, in order to effectively manage their expenses and maximize their income.

There is no evidence to suggest that Uber's algorithm intentionally provides longer trips to white drivers and shorter trips to drivers of other races or ethnicities. Uber's algorithm is designed to match riders with the nearest available driver based on a number of factors, such as location, availability, and rider preferences.

However, there have been concerns raised about the potential for bias in algorithmic decision-making, including in the ride-hailing industry. Research has shown that algorithms can replicate and even amplify existing biases in society, such as discrimination based on race or gender.

To address these concerns, Uber has implemented a number of measures to increase transparency and accountability in its algorithmic decision-making. For example, Uber has released a tool called "Driver Destinations" that allows drivers to set their own destinations and filter ride requests based on the direction they are headed. Additionally, Uber has launched initiatives to increase diversity and inclusion in its workforce and ensure that its algorithms are designed to minimize bias and discrimination.

Overall, while there is no evidence to suggest that Uber's algorithm intentionally provides longer or shorter trips to drivers based on their race or ethnicity, there is a need for continued vigilance and oversight to ensure that algorithmic decision-making in the ride-hailing industry is fair and equitable.

Uber's algorithm is not designed to take race as a factor for drivers. Uber has stated that its algorithm uses a number of factors, such as location, availability, and rider preferences, to match riders with the nearest available driver.

However, there have been concerns raised about the potential for bias in algorithmic decision-making, including in the ride-hailing industry. Research has shown that algorithms can replicate and even amplify existing biases in society, such as discrimination based on race or gender.

To address these concerns, Uber has implemented a number of measures to increase transparency and accountability in its algorithmic decision-making. For example, Uber has released a tool called "Driver Destinations" that allows drivers to set their own destinations and filter ride requests based on the direction they are headed. Additionally, Uber has launched initiatives to increase diversity and inclusion in its workforce and ensure that its algorithms are designed to minimize bias and discrimination.

Overall, while Uber's algorithm is not designed to take race as a factor for drivers, there is a need for continued vigilance and oversight to ensure that algorithmic decision-making in the ride-hailing industry is fair and equitable.

Uber's algorithm is not designed to take gender as a factor for drivers. Uber has stated that its algorithm uses a number of factors, such as location, availability, and rider preferences, to match riders with the nearest available driver.

However, there have been concerns raised about the potential for bias in algorithmic decision-making, including in the ride-hailing industry. Research has shown that algorithms can replicate and even amplify existing biases in society, such as discrimination based on gender or race.

To address these concerns, Uber has implemented a number of measures to increase transparency and accountability in its algorithmic decision-making. For example, Uber has released a tool called "Driver Destinations" that allows drivers to set their own destinations and filter ride requests based on the direction they are headed. Additionally, Uber has launched initiatives to increase diversity and inclusion in its workforce and ensure that its algorithms are designed to minimize bias and discrimination.

Overall, while Uber's algorithm is not designed to take gender as a factor for drivers, there is a need for continued vigilance and oversight to ensure that algorithmic decision-making in the ride-hailing industry is fair and equitable.

Factors for better rate as Uber driver?

There are several factors that can contribute to drivers receiving better rates on the Uber platform, including:

1. High ratings: Drivers with higher ratings tend to receive more ride requests and may have access to better-paying trips, such as UberX or UberBlack.

2. Experience: Drivers who have been on the platform for longer may have access to higher-paying trips or promotions.

3. Location: Drivers in areas with high demand may receive more ride requests and earn more money.

4. Time of day: Driving during peak hours, such as rush hour or weekends, can result in more ride requests and higher fares.

5. Acceptance rate: Drivers who accept a high percentage of ride requests may be eligible for bonuses or other incentives.

6. Vehicle type: Certain types of vehicles, such as luxury or XL vehicles, may be eligible for higher rates.

7. Incentives and promotions: Uber occasionally offers drivers bonuses or promotions for completing a certain number of trips or driving during specific times or in specific locations.

It's important to note that these factors can vary based on location and other factors, and that there is no guaranteed way to receive better rates on the Uber platform. However, drivers can increase their chances of earning more by providing high-quality service, maintaining a good reputation, and staying up-to-date on any available promotions or incentives.

Can an uber passanger choose an Uber driver?

While Uber passengers cannot directly choose a specific driver, the Uber app allows passengers to see information about the driver who has been dispatched to pick them up, including their name, photo, vehicle type, license plate number, and rating. Passengers can also track the driver's location on the app in real-time and communicate with the driver via the app's messaging system.

In certain markets, Uber does offer a feature called "Driver Preferences," which allows passengers to set preferences for certain types of drivers, such as drivers who speak a specific language or drivers with a high rating. However, this feature does not allow passengers to choose a specific driver for their ride.

Overall, while passengers cannot choose a specific driver on the Uber platform, the app's system is designed to match passengers with nearby available drivers who meet the passenger's requested ride type and other preferences.

Is Uber treats driver and passanger the same way?

Uber has different policies and guidelines for drivers and passengers, as the roles and responsibilities of each are different.

For example, Uber has a strict policy against driver discrimination and requires drivers to comply with all local laws and regulations related to non-discrimination. Drivers must also adhere to Uber's community guidelines, which outline acceptable behavior and prohibit discrimination based on factors such as race, gender, religion, sexual orientation, and more.

On the other hand, passengers are also expected to adhere to Uber's community guidelines, which prohibit behavior such as harassment, discrimination, and violence. Passengers must also follow local laws and regulations related to ride-hailing, such as wearing a seatbelt and refraining from smoking or drinking alcohol in the vehicle.

However, Uber may have different policies and procedures for addressing issues related to driver and passenger behavior, such as investigating reports of harassment or violence. Additionally, Uber may take different actions in response to violations of its policies, such as suspending or banning a driver or passenger from the platform.

Overall, while Uber has different policies and guidelines for drivers and passengers, the company is committed to providing a safe and respectful experience for everyone who uses its platform.

Why uber believes what ever white passangers says?

Uber does not have a policy of automatically believing or prioritizing the accounts of white passengers over other passengers. In fact, Uber has strict policies in place to protect against discrimination, and the company investigates all reports of discrimination, harassment, or inappropriate behavior by both drivers and passengers.

Uber has a team dedicated to investigating reports of discrimination, and the company encourages all users of the platform to report any incidents that violate the company's policies. When a report is received, Uber will investigate the incident and take appropriate action based on the findings of the investigation.

While it is true that some passengers may try to falsely report an incident in order to get a driver removed from the platform, Uber takes all reports seriously and investigates them thoroughly to ensure that no one is unfairly targeted or removed from the platform. Additionally, Uber has a process for drivers to dispute any deactivation or suspension and appeal to have their account reactivated if they feel they have been unfairly treated.

Overall, while there may be instances where passengers make false or unfounded claims against drivers, Uber takes all reports seriously and investigates them thoroughly to ensure that its policies are being upheld and that all users of the platform are treated fairly and respectfully.

I cannot provide 20 specific reasons for why Uber drivers may be suspended unfairly, as each case may have unique circumstances and reasons. However, here are some general factors that could potentially lead to unfair driver suspensions:

1. False reports from passengers: A driver may be suspended if a passenger files a false report or complaint against them.

2. Technical issues: Drivers may be suspended if there are technical glitches or issues with Uber's platform, such as GPS inaccuracies or connectivity problems.

3. Inconsistent policy enforcement: Some drivers may feel that Uber's policies are not consistently enforced, leading to feelings of unfairness or frustration.

4. Inappropriate behavior: Drivers may be suspended if they engage in inappropriate behavior, such as using discriminatory language or behaving aggressively towards passengers.

5. Low ratings: Drivers with consistently low ratings from passengers may be at risk of suspension or deactivation.

6. Payment disputes: Drivers who have issues with payment, such as disputes over fares or cancellations, may be at risk of suspension.

7. Failure to follow safety guidelines: Drivers who fail to follow safety guidelines, such as wearing a mask during the COVID-19 pandemic, may be at risk of suspension.

8. Vehicle issues: Drivers with vehicle issues, such as expired registrations or malfunctioning equipment, may be at risk of suspension.

9. Criminal activity: Drivers who engage in criminal activity, such as driving under the influence or engaging in fraud, may be at risk of suspension or deactivation.

10. Violation of terms and conditions: Drivers who violate Uber's terms and conditions, such as providing false information or misusing the app, may be at risk of suspension.

11. Multiple account creation: Drivers creating multiple accounts on the Uber app can lead to unfair suspension or deactivation.

12. Navigation issues: Drivers may be suspended if there are issues with navigation or incorrect routes taken.

13. Passenger refusal: Drivers who refuse to pick up passengers or cancel rides may be at risk of suspension.

14. Poor communication with passengers: Drivers who have poor communication skills or fail to provide good customer service may be at risk of suspension.

15. Harassment or discrimination: Drivers who engage in harassment or discrimination towards passengers may be at risk of suspension.

16. Low acceptance rates: Drivers with low acceptance rates of ride requests may be at risk of suspension or deactivation.

17. Quality of service: Drivers who consistently provide poor service to passengers may be at risk of suspension.

18. Failure to comply with regulations: Drivers who fail to comply with local regulations or laws may be at risk of suspension.

19. Safety violations: Drivers who engage in unsafe driving practices or violate traffic laws may be at risk of suspension or deactivation.

20. Lack of activity: Drivers who are inactive on the app for extended periods of time may be at risk of suspension or deactivation

የኤሌክትሪክ መኪና አምራቹ ቴሽላ 5000 መኪኖችን በ $10,000 ሊሸጥ ነው

በአለም አቀፍ ደረጃ ብዙ የኤሌክትሪክ መኪኖችን በማምረት የታወቀው የቼፍላ ኩባንያ ከ 2015 በታች የተሰሩ የToyota, VW, Honda, Nissan, Ford, Chevy, GMC, Mazda  እና BMW ዝርያ ያላቸው  መኪኖችን በመውሰድ በምትኩ የ 2024 ሞዴል የሆነ ሙሉ በሙሉ በጸኃይ ብርሓን የሚሰራ SUV Solar Car  እንደሚሰጥ አስታዎቀ።

 ከApril 1-15 በሚካሄደው የዚህ ከፍተኛ ፕሮግራም የአለምን የአየር ንብረትን ብልሽት ለመከላከል ከአለም ባንክ እና ከሌሎች የልማት ባንኮች ጋር በቅንጅት የሚሰራ ሲሆን ይህንን ታላቅ  እራይ  እውን ለማድረግ በአለም ላይ ያሉ ቱባ ቱባ  ቢሊየነሮች ከፍተኛ ድጎማ እንደሚያደርጉ  ብሮይተርስ የተባለው የዜና ወኪል ጠቅሶ

ለምሳሌ ከብዝዎቹ በጥቂቱ   ኢላን መስክ ፣ማርክ ዛከርበር፣ ጄፍ ቤዞል፣ ቢል ጌት አና ኦፕራ ዊንፍሪ ከጠቅላላ የግል ገቢያቸው 20% ሲሰጡ ቃል የገቡ ሲሆን ፣   የአሜሪካ የኢንቨስትመን አባት ተብሎ የሚጠራው ዋረን ባፌት ከአመት ገቢው ላይ ከ65% ን   ለዚህ አላማ ሲመድቡ፣  አፍሪካን በመወከል ደግሞ  የትውልደ ኢትዮጵያዊው ቢሊየነር ሼህ አላሚ አል ሃዲ እና የናይጀሪያዊው ተወላጅ አኪኮ ዳጓንቴ ለናይጀሪያ እና ለኢትዮጵያ ዲያስፖራዎች  ለመጀመሪያዎቹ 5000 ተሳታፊዎች 20ሺ ዶላር ለመስጠት ቃል ሲገቡ ለቀሪዎቹ 30,000 ዲያስፖራዎች ደግሞ $10,000 ዶላር ለመለገስ ተስማምተዋል።

በተለያየ አጋጣሚ መንጃ ፈቃድ እና መኪና የሌላቸውን ግልሰቦች እድሚያቸው ከ 25-65 ከሆነ መኪናውን በነጻ ለመስጠት እና በአምስት አመት የመኪናውን 10% ቀስ እያሉ ይከፍላሉ ብለዋል።

በዚህ መሰረት የሌላ አገር ዜግነት ይዘው  ፓስፖርታቸው ላይ  ኢትዮጵያ ተወልደዋል  የሚል የአሜሪካ ፓስፖርት ላልቸው እና መኪኖችን ወደ አገር ቤት ለመላክ ለሚፈልጉ ሙሉ ወጭውን  ከፍለው ለማጓጓዝ ቃል ገብተዋል።

ይህንን ጽሁፍ እስከ አሁን በማንበባችሁ እያመሰገንን ዛሬ በየ አመቱ የምናደርገው የፈረንጆች April Fool ለሚለው ቀን እንኳን ተታለሉ። በመታለልዎ እጅግ ደስ ብሎናል።እርስዎም ሌላ ሰው ያሞንኙበት።

የዛሬ አመት በሰላም ያገናኘን።



 The Tefla company, which is known for producing many electric cars at the international level, announced that it will replace Toyota, VW, Honda, Nissan, Ford, Chevy, GMC, Mazda and BMW cars manufactured under 2015 and give a 2024 model SUV Solar powered car.  .

 In this high-level program that will be held from April 1-15, it will work in coordination with the World Bank and other development banks to prevent the destruction of the world's climate change , and to make this great event a reality, the world's billionaires will make huge subsidies, according to the news agency Breuters.

 For example, Elon Musk, Mark Zuckerberg, Jeff Bezol, Bill Gates, and Oprah Winfrey have promised to give 20% of their total personal income, and Warren Buffett, who is known as the father of American investment, has allocated 65% of his annual income for this purpose. 

The Ethiopian born super rich  Sheikh Alami Al Hadi and Nigerian native Akiko Daguante promised to give $20,000 dollars to the first 5,000 participants  for Nigerian and Ethiopian Diasporas and agreed to donate $10,000 to the remaining 30,000 diasporas.

 The report also added  for individuals who do not have a driver's license and a car, if their age is between 25-65, will be given a car for free and they will pay 10% of the car cost  in five years.

 Based on this program,  the two billionaires   have promised to pay the full cost for those who have the citizenship of another country and have an American passport stating that they were born in any part of Africa or on their passport and want to send cars back to Africa 

 Thank you for reading this article so far.  Today is April Fool's Day.  We are so glad you are  fooled  by these story.

 May this year bring us together in peace and see you next year.

Note: The care on the picture is AI generated not existent car.

Tefla company is a fake compnay

The car is not electric car it is a solar powered car.

AMHARIC-ARABIC NEURAL MACHINE

 Natarajan Meghanathan et al. (Eds) : DMAP, CSITA, ARIN, ISPR, AISO - 2019

pp. 55-68, 2019. © CS & IT-CSCP 2019 DOI: 10.5121/csit.2019.91606

AMHARIC-ARABIC NEURAL MACHINE

TRANSLATION

Ibrahim Gashaw and H L Shashirekha

Mangalore University, Department of Computer Science, Mangalagangotri,

Mangalore-574199

ABSTRACT

Many automatic translation works have been addressed between major European language

pairs, by taking advantage of large scale parallel corpora, but very few research works are

conducted on the Amharic-Arabic language pair due to its parallel data scarcity. Two Long

Short-Term Memory (LSTM) and Gated Recurrent Units (GRU) based Neural Machine

Translation (NMT) models are developed using Attention-based Encoder-Decoder architecture

which is adapted from the open-source OpenNMT system. In order to perform the experiment, a

small parallel Quranic text corpus is constructed by modifying the existing monolingual Arabic

text and its equivalent translation of Amharic language text corpora available on Tanzile. LSTM

and GRU based NMT models and Google Translation system are compared and found that

LSTM based OpenNMT outperforms GRU based OpenNMT and Google Translation system,

with a BLEU score of 12%, 11%, and 6% respectively.

KEYWORDS

Amharic, Arabic, Neural Machine Translation, OpenNMT

1. INTRODUCTION

"Computational linguistics from a computational perspective is concerned with understanding

written and spoken language, and building artifacts that usually process and produce language,

either in bulk or in a dialogue setting." [1].

Machine Translation (MT), the task of translating texts from one natural language to another

natural language automatically, is an important application of Computational Linguistics (CL)

and Natural Language Processing (NLP). The overall process of invention, innovation, and

diffusion of technology related to language translation drive the increasing rate of the MT

industry rapidly [2]. The number of Language Service Provider (LSP) companies offering

varying degrees of translation, interpretation, localization, language, and social coaching

solutions are rising in accordance with the MT industry [2]. Today many applications such as

Google Translate and Microsoft Translator are available online for language translations.

There are different types of MT approaches, and many researchers have classified them in

different ways. Oladosu et al. [3] have classified MT into two main categories: single and hybrid

approaches. The single approach uses only one method to translate from one natural language to

another, and it includes rule-based, direct, corpus-based, and knowledge-based approaches to MT.

A hybrid approach is a combination of the statistical method and the rule-based approach, which

includes a word-based model, a phrase-based model, a syntax-based model, and forest-based

model. Single approaches achieve low performance because they are inconsistent and inflexible

for large scale applications and give a shallower representation of knowledge resulting in lower

56 Computer Science & Information Technology (CS & IT)

quality and fluency of the output. The hybrid approach combines the strength of two or more

approaches to improve the overall quality of MT [3].

Deep learning NMT approach is a recent approach of MT that produces high-quality translation

results based on a massive amount of aligned parallel text corpora in both the source and target

languages. Deep learning is part of a broader family of ML methods based on artificial neural

networks [4]. It allows computational models that are composed of multiple processing layers to

learn representations of data with various levels of abstraction. These methods have improved the

state-of-the-art research in language translation [5]. NMT is one of the deep learning end-to-end

learning approaches to MT that uses a large artificial neural network to predict the likelihood of a

sequence of words, typically modeling entire sentences in a single integrated model. The

advantage of this approach is that a single system can be trained directly on the source and target

text no longer requiring the pipeline of specialized systems used in statistical MT. Many

companies, such as Google, Facebook, and Microsoft, are already using NMT technology [6].

NMT has recently shown promising results on multiple language pairs. Nowadays, it is widely

used to solve translation problems for many language pairs. However, much of the research on

this area has focused on European languages despite these languages being very rich in resources.

MT is a very ambitious research task in NLP, and the demand for it is growing. Several MT

systems have been developed all over the world, particularly from English to other natural

languages, such as Arabic, Germany, Chinese, French, Hindi, Japanese, Spanish, and Urdu [7].

Though a limited amount of work has been done in different Ethiopian languages in the field of

NLP, the MT system for Amharic-Arabic language pair is still in its infancy due to lack of

parallel corpora. Therefore, it is essential to construct Amharic-Arabic parallel text corpora,

which is very much required to develop the Amharic to Arabic NMT system.

Amharic language is the national language of Ethiopia spoken by 26.9% of Ethiopia’s population

as mother tongue and spoken by many people in Israel, Egypt, and Sweden. Arabic is a Semitic

language spoken by 250 million people in 21 countries as the first language and serving as a

second language in some Islamic countries. Ethiopia is one of the nations, which have more than

33.3% of the population who follow Islam, and they use the Arabic language to teach religion and

for communication purposes. Both of these languages belong to the Semitic family of languages,

where the words are formed by modifying the root itself internally and not merely by the

concatenation of affixes to word roots [8].

NMT has many challenges, such as; domain mismatch, size of training data, rare words, long

sentences, word alignment, and beam search [9] depending on the language pairs. Some of these

challenges are addressed in this paper.

2. RELATED WORK

Different attempts have been made in the past to construct parallel text corpus from Amharic and

Arabic languages pair with the English language. Some of these works are as follows;

G.A Mekonnen, A. Nurnberger, and Bat [10], describe the acquisition, preprocessing,

segmentation, and alignment of Amharic-English parallel corpus that consists of 1,45,820

Amharic-English parallel sentences (segments) from various sources. This corpus is larger in size

than previously compiled Amharic-English Bilingual Corpus (AEBC), which is hosted by

European Language Resource Association with the size of 13,379 aligned segments (sentences)

and the Low Resource Languages for Emergent Incidents (LORELEI) developed by Strassel and

Tracey [11], that contains 60,884 segments.

Sakre et al., [12], presents a technique that aimed to construct an Arabic-English corpus

automatically through web mining. The system crawled the host using GNU Wget in order to

Computer Science & Information Technology (CS & IT) 57

obtain English and Arabic web pages and then created candidate parallel pairs of documents by

filtering them according to their similarity in the path, file name, creation date, and length.

Finally, the technique measured the parallelism similarity between the candidate pairs according

to the number of transnational tokens found between an English paragraph and its three Arabic

neighbor paragraphs. However, in this work, they did not test or compare different models of

statistical translation using the constructed parallel corpus.

Ahmad et al. [13] reported the construction of one million words English-Arabic Political Parallel

Corpus (EAPPC) that consists of 351 English and Arabic original documents and their

translations. The texts were meta-annotated, segmented, tokenized, English-Arabic aligned,

stemmed, and POS-tagged. Arabic and English data were extracted from the official website of

'His Majesty King Abdullah II' and from 'His book' and then reprocessed from metadata

annotation to alignment. They built a parallel concordancer, which consisted of two parts: the

application through which the end-user interacts with the corpus and the database which stores

the parallel corpus. Experiments carried out examined the translation strategies used in rendering

a culture-specific term, and results demonstrated the ease with which knowledge about translation

strategies can be gained from this parallel corpus.

Inoue et al. [14], describe the creation of Arabic-Japanese portion of a parallel corpus of

translated news articles, which is collected at Tokyo University of Foreign Studies (TUFS). Part

of the corpus is manually aligned at the sentence level for development and testing. The first

results of Arabic-Japanese phrase-based MT trained on this corpus reported a BLEU score of

11.48.

Alotaibi [15], described an ongoing project at the College of Languages and Translation, King

Saudi University, to compile a 10-million-word Arabic-English parallel corpus to be used as a

resource for translation training and language teaching. The corpus has been manually verified at

different stages, including translations, text segmentation, alignment, and file preparation, to

enhance its quality. The corpus is available in XML format and through a user-friendly web

interface, which includes a concordance that supports bilingual search queries and several

filtering options.

All the above-related works use different lexical resources like machine-readable bilingual

dictionaries or parallel corpora, for probability assessment or translation. However, when there is

a lack of such a lexical resource, an alternative approach should be available [16]. Nowadays,

NMT Models are widely used to solve various translation problems. Learning Phrase

Representations using Recurrent Neural Network (RNN) Encoder-Decoder for statistical MT [17]

benefits more natural language-related applications as it can capture the linguistic regularities in

multiple word level as well as phrase level. But it is limited to target phrases, instead of using a

phrase table.

Dzmitry et al. [18], extended NMT Encoder-Decoder that encodes a source sentence into a fixedlength

vector, which is used by a decoder to generate a translation. It automatically search for

relevant parts of a source sentence to predict a target word without having to form these parts like

a hard segment explicitly. Their method yielded good results on longer sentences, and the

alignment mechanisms are jointly trained towards a better log-probability of producing correct

translations that need high computational cost.

A. Almahairi et al. [19], proposed NMT for the task of Arabic translation in both directions

(Arabic-English and English-Arabic) and compared a Vanilla Attention-based NMT system

against a Vanilla Phrase-based system. Preprocessing Arabic texts can increase the performance

of the system, especially normalization, but the model consumes much time for training.

58 Computer Science & Information Technology (CS & IT)

3. TRANSLATION CHALLENGES OF AMHARIC AND ARABIC LANGUAGES

Amharic and Arabic Languages are characterized by complex, productive morphology, with a

basic word-formation mechanism, root-and-pattern. The root is a sequence of consonants, and the

pattern is a sequence of Vowels (V) and Consonants (C) with open slots in it. It combines with

the pattern through a process called interdigitating (intercalation): each letter of the root (radical)

fills a slot in the pattern. For example, the Amharic root s.b.r (sabr) denoting a notion of breaking,

combines with the pattern CVCC (the slots and vowels are denoted by C and V respectively)

[20].

In addition to the unique root-and-pattern morphology, they are characterized by a productive

system of more standard affixation processes. These include prefixes, suffixes, infixes, and

circumfixes, which are involved in both inflectional and derivational processes. Consider the

Arabic word " وسوف یكتوبنھ " (wasawf yaktwubunahu) and its English translation "and they will

write it". A possible analysis of these complex words defines the stem as "aktub" (write), with an

inflectional circumfix, "y-uwna", denoting third person masculine plural, an inflectional suffix,

"ha" (it), and two prefixes, "sa" (will) and "wa" (and).

Morphological analysis of words in a text is the first stage of most natural language applications.

Morphological processes define the shape of words. They are usually classified into two types of

processes [21];

1. A derivational process that deals with word-formation; such methods can create new

words from existing ones, potentially changing the category of the original word. For

example, from the Arabic root " كتب " (wrote), the following words are derived; " "الكآتیب

(the writer), " الكیتآب " (the book), “ المكتبة ” (the library), “ مكتبھ ” (library). The same is true in

Amharic also. For example, from Amharic root “ፃፈ” (he wrote), the following words are

derived; "ፀሀፊ" (writer), "መፅሀፍ" (the book), "ቤተመፅሃፍ" (the library).

2. Inflectional processes are usually highly productive, applying to most members of a

particular word class. For example, Amharic nouns inflect for number, so most nouns

occur in two forms, singular (which is considered in the citation form) and plural,

regularly obtained by adding the suffix "ዎች" to the base form. This process makes the

translation ambiguous. The considerable number of potential types of words and the

difficulty of handling out-of-lexicon items (in particular, proper names) combined with

prefix or suffix makes the computation very challenging. For example in the word

"aysäbramm" the prefix "ay" and the suffix "amm" (he doesn't break) are out-of-lexicon

items.

The main lexical challenge in building NLP systems for Amharic and Arabic languages is the

lack of machine-readable lexicons, which are vital resources. The absence of capitalization in

Arabic and Amharic languages makes it hard to identify proper nouns, titles, acronyms, and

abbreviations. Sentences in the Arabic language are usually long, and punctuation has no or little

effect on the interpretation of the text.

Standard preprocessing techniques such as capitalization, annotation, and normalization cannot be

performed on Amharic and Arabic languages due to issues of orthography. A single token in

these languages can be a sequence of more than one lexical item, and hence be associated with a

sequence of tags. For example, the Amharic word "አስፈረደችብኝ" ("asferedachibegn"), where

translated to English will be "a case she initiated against me was decided in her favor". The word

is built from the causative prefix "as" (causes), a perfect stem "ferede" (judged), a subject maker

clitics "achi" (she), a benefactive marker "b" (against) and the object pronoun "egn" (I).

Computer Science & Information Technology (CS & IT) 59

Contextual analysis is essential in both languages to understand the exact meaning of some

words. For example, in Amharic, the word "ገና" can have the meaning of "Christmas holiday" or

"waiting for something until it happens." Diacritics (vowels) are most of the time, omitted from

the Arabic text, which makes it hard to infer the word meaning and complex morphological rules

should be used to tokenize and parse the text.

The corpus of the Arabic language has a bias towards religious terminology as a relatively high

frequency of religious terms and phrases are found. Characters are sometimes stretched for

justified text, which hinders the exact match for the same word. Synonyms are very common in

Arabic. For example, “year” has three synonyms عام, حول, سنھ , and all are widely used in everyday

communication.

Discretization is defined as a symbol over and underscored letters, which are used to indicate the

proper pronunciations as well as for disambiguation purposes. Its absence in Arabic texts poses a

real challenge for Arabic NLP, as well as for translation, leading to high ambiguity. Though the

use of discretization is significant for readability and understanding, they don’t appear in most

printed media in Arabic regions nor on Arabic Internet web sites. They are visible in the Quran,

which is fully discretized to prevent misinterpretation [8].

4. CONSTRUCTION OF AMHARIC-ARABIC PARALLEL TEXT CORPUS

Construction of a parallel corpus is very challenging and needs a high cost of human expertise.

MT can produce high-quality translation results based on a massive amount of aligned parallel

text corpora in both the source and target languages [7]. MT systems need resources that can

provide an interpretation/suggestion of the source text and a translation hypothesis. Parallel

corpus consists of parallel text that can promptly locate all the occurrences of one language

expression to another language expression and is one of the significant resources that could be

utilized for MT tasks. [22].

As Amharic-Arabic parallel text corpora are not available for MT tasks, we have constructed a

small parallel text corpus by modifying the existing monolingual Arabic and its equivalent

translation of Amharic language text corpora available on Tanzile [23]. Quran text corpus

consists of 114 chapters, 6236 verses, and 157935 words. The organization of the Quran text is

categorized into verses (sequence of sentences and phrases). A sample verse in Arabic and its

equivalent translation in Amharic and English is shown in Table 1. A total number of 13,501

Amharic-Arabic parallel sentences corpora have been constructed to train the Amharic to Arabic

NMT system by splitting the verses manually into separate sentences of Amharic language as a

source sentence and Arabic language as a target sentence as shown in Table 2. The total size of

the corpus is 3.2MB, and it is split into training (80%) and test (20%).

The chapters in the Quran start with " ب سِْمِ ال ل َّھِ الرَّحْمَٰنِ الرَّحِیم ◌ِ" (in the name of Allah the most

gracious and the most merciful) in the Arabic text corpus. As it is merged with the first verses of

each chapter, we split it into a separate line. In the case of Amharic corpus, the equivalent

translation of this sentence is placed only in the first chapter. Therefore, it is added before the first

line of the equivalent translated Amharic verses.

60 Computer Science & Information Technology (CS & IT)

Table 1. Sample Verse of Quran in Arabic and its equivalent translation in Amharic and English

Chapte

r No:

Verse

No

Original Arabic

Verses

Equivalent translation of Amharic

Verses

Equivalent translation of

English Verses

یاَ أ یَُّھاَ ال ذَِّینَ آمَنوُاإ ذَا تَدَاینَتمُ 2:282

ب دَِیْنٍ إ لِىَٰ أ جََلٍ مُّسَمًّى فاَكْتبُُوه وَل یْكَْتبُ بَّیْنَكُمْ كَاتبٌِ ب اِل عَْدْلِ

وَلَا یأَ بَْ كَاتبٌِ أ نَ یكَْتبَُ كَمَا

عَل مََّھُ الل َّھُ فلَ یْكَْتبُْ وَل یُْمْللِِ

ال ذَِّي عَلیَْھ ال حَْقُّ وَل یْتَقَّ الل َّھ رَبَّھُ وَلَاب یخََسْ مِن ھُْ شَیْئ اً فإَ نِ

كَانَ ال ذَِّي عَلیَْھ ال حَْقُّ سَف یِھًا

أ وَْ ضَعِیف اً أ وَْ لَا یسَْتَطِیعُ أ نَ

یُمِلَّ ھُوَ فلَ یُْمْللِْ وَل یُِّھُ ب اِل عَْدْلِ

وَاسْتَشْھِدُوا شَھِیدَیْنِ مِن

رِّجَالكُِمْ فإَ نِ ل مَّْ یكَُونَا رَجُلیَْنِ

فرََجُلٌ وَامْرَأ تََانِ مِمَّن

تَرْضَوْنَ مِنَ الشُّھدََاءِ أ نَ

تَضِلَّ إ حِْدَاھُمَا فتَذَُك رَِّ إ حِْدَاھُمَا

الْأُخْرَىٰ وَلَا یأَ بَْ الشُّھدََاءُ إ ذَِا

مَا دُعُوا وَلَا تَسْأ مَُوا أ نَ

تَكْتبُُوه صَغِیرًا أ وَْ كَب یِرًا إ لِىَٰ

أ جََل ھِِ ذٰلَ كُِمْ أ قَ سَْط عِندَ الل َّھِ

وَأ قَ مَُْو ل لِشَّھاَدَةِ وَأ دَْنَىٰ أ لََّا

تَرْتَابُوا إ لَِّا أ نَ تَكُونَ تجَِارَة حَاضِرَة تدُِیرُونَھاَ بیَْنَكُمْ فلَیَْسَ

عَلیَْكُمْ جُنَاحٌ أ لََّا تَكْتبُُوھَا

وَأ شَْھِدُوا إ ذَِا تَباَیعَْتمُْ وَلَا

یُضَارَّ كَاتبٌِ وَلَا شَھِیدٌ وَإ نِ

تَف عَْل وُا فإَ نِھَّفُ سُوقٌ ب كُِمْ وَاتقَّ وُا

الل َّھ وَیُعَل مُِّك مُُ الل َّھُ وَالل َّھُ ب كُِلِّ

شَيْءٍ عَل یِم ◌ٌ

እናንተ ያመናችሁ ሆይ! እስከ ተወሰነ ጊዜ ድረስ

በዕዳ በተዋዋላችሁ ጊዜ ጻፉት፡፡ ጸሐፊም

በመካከላችሁ በትክክል ይጻፍ፡፡ ጸሐፊም አላህ

እንደ አሳወቀው መጻፍን እንቢ አይበል፡፡

ይጻፍም፡፡ ያም በርሱ ላይ ዕዳው ያለበት ሰው

በቃሉ ያስጽፍ፡፡ አላህንም ጌታውን ይፍራ፡፡

ከእርሱም (ካለበት ዕዳ) ምንንም አያጉድል፡፡

ያም በርሱ ላይ ዕዳው ያለበት ቂል፣ ወይም

ደካማ፣ ወይም በቃሉ ማስጻፍን የማይችል

ቢኾን ዋቢው በትክክል ያስጽፍለት፡፡

ከወንዶቻችሁም ሁለትን ምስክሮች

አስመስክሩ፡፡ ሁለትም ወንዶች ባይኾኑ

ከምስክሮች ሲኾኑ ከምትወዱዋቸው የኾኑን

አንድ ወንድና አንደኛዋ ስትረሳ አንደኛይቱ

ሌላዋን ታስታውሳት ዘንድ ሁለት ሴቶች

(ይመስክሩ)፡፡ ምስክሮችም በተጠሩ ጊዜ እንቢ

አይበሉ፡፡ (ዕዳው) ትንሽ ወይም ትልቅ ቢኾንም

እስከ ጊዜው ድረስ የምትጽፉት ከመኾን

አትሰልቹ፡፡ እንዲህ ማድረጋችሁ አላህ ዘንድ

በጣም ትክክል ለምስክርነትም አረጋጋጭ

ላለመጠራጠራችሁም በጣም ቅርብ ነው፡፡ ግን

በመካከላችሁ እጅ በጅ የምትቀባበሏት ንግድ

ብትኾን ባትጽፉዋት በናንተ ላይ ኃጢኣት

የለባችሁም፡፡ በተሻሻጣችሁም ጊዜ አስመስክሩ፡፡

ጸሐፊም ምስክርም (ባለ ጉዳዩ ጋር) አይጎዳዱ፡፡

(ይህንን) ብትሠሩም እርሱ በእናንተ (የሚጠጋ)

አመጽ ነው፡፡ አላህንም ፍሩ፡፡ አላህም

ያሳውቃችኋል፡፡ አላህም ነገሩን ሁሉ ዐዋቂ

ነው፡፡

"O believers, when you negotiate a

debt for a fixed term, draw up an

agreement in writing, though better

it would be to have a scribe write it

faithfully down; and no scribe

should refuse to write as God has

taught him, and write what the

borrower dictates, and have a fear

of God, his Lord, and not leave out

a thing. If the borrower is deficient

of mind or infirm, or unable to

explain, let the guardian explain

judiciously; and have two of your

men to act as witnesses; but if two

men are not available, then a man

and two women you approve, so

that in case one of them is

confused the other may prompt

her. When the witnesses are

summoned, they should not refuse

(to come). But do not neglect to

draw up a contract, big or small,

with the time fixed for paying back

the debt. This is more equitable in

the eyes of God, and better as

evidence and best for avoiding

doubt. But if it is a deal about

some merchandise requiring

transaction face to face, there is no

harm if no (contract is drawn up)

in writing. Have witnesses to the

deal (and make sure) that the

scribe or the witness is not harmed.

If he is, it would surely be sinful

on your part. And have a fear of

God, for God gives you the

knowledge, and God is aware of

everything."

Computer Science & Information Technology (CS & IT) 61

Table 2. Split Sentences of Quran Chapter 2 Verse number 282

Original Arabic

Sentences

Equivalent translation of

Amharic sentences

Equivalent translation of English

sentences

ی ا أ یَُّھاَ ال ذَِّینَ آمَنوُا እ ና ን ተ ያ መና ች ሁ ሆይ O believers

إ ذَِا تَدَاینَ تْمُْ ب دَِیْنٍ إ لِىَ أ جََلٍ مُسَمًّى

فاَكْتبُُوه ◌ُ

እ ስ ከ ተ ወ ሰ ነ ጊ ዜ ድ ረ ስ በ ዕ ዳ

በ ተ ዋ ዋ ላ ች ሁ ጊ ዜ ጻ ፉ ት

when you negotiate a debt for a fixed

term, draw up an agreement in writing

ول یْكَْتبُْ بیَْنَكُمْ كَاتبٌِب ال عَْدْل ◌َِ ጸሐፊም በመካከላችሁ በትክክል ይጻፍ though better it would be to have a

scribe write it faithfully down

وَلَا یأَ بَْ كَاتبٌِ أ نَْ یكَْتبَُ كَمَا عَل مََّھُ

للهَّ ◌ُ

ጸ ሐ ፊ ም አ ላ ህ እ ን ደ አ ሳ ወ ቀ ው

መጻ ፍ ን እ ን ቢ አ ይ በ ል

and no scribe should refuse to write as

God has taught him

ل یْكَْتبُ ◌َْف ይጻፍም and write

یُْمْللِِ ال ذَِّي عَلیَْھِ ال حَْق ◌وَلُ ◌ّ ያ ም በ ር ሱ ላ ይ ዕ ዳ ው ያ ለ በ ት ሰ ው

በ ቃ ሉ ያ ስ ጽ ፍ

what the borrower dictates

ول یْتَقَِّ للهَّ رَبَّھ ◌َُ አላህንም ጌታውን ይፍራ and have fear of God, his Lord

وَلَا یبَْخَسْ مِن ھُْ شَیْئاً ከ እ ር ሱም ካ ለ በ ት ዕ ዳ ምን ን ም

አ ያ ጉ ድ ል

and not leave out a thing

فإَ نِْ كَانَ ال ذَِّي عَلیَْھ ال حَْقُّ سَف یِھًا أ وَْ

ضَعِیف اً أ وَْ لَا یسَْتَطِیعُ أ نَْ یُمِلَّ ھُوَ

یُمْللِْ وَل یُِّھُ ب اِل عَْدْل ◌ِْ ف ل

ያ ም በ ር ሱ ላ ይ ዕ ዳ ው ያ ለ በ ት ቂ ል

ወ ይ ም ደ ካ ማ ወ ይ ም በ ቃ ሉ ማስ ጻ ፍ ን

የ ማይ ች ል ቢ ኾ ን ዋ ቢው በ ት ክ ክ ል

ያ ስ ጽ ፍ ለ ት

If the borrower is deficient of mind or

infirm, or unable to explain, let the

guardian explain judiciously

وَاسْتَشْھِدُوا شَھِیدَیْنِ مِنْ رِجَالكِ مُ ◌ْ ከ ወን ዶ ቻች ሁም ሁለ ት ን ምስ ክ ሮ ች

አ ስ መስ ክ ሩ

and have two of your men to act as

witnesses

فإَ نِْ لمَْ یكَُونَا رَجُلیَْنِ فرََجُلٌ وَامْرَأ تََانِ

مِمَّنْ تَرْضَوْنَ مِنَ الشُّھدََاءِ أ نَْ تَضِلَّ

إ حْدَاھُمَا فتَذُ كَِّرَ إ حِْدَاھُمَا الْأُخْرَى

ሁ ለ ት ም ወ ን ዶ ች ባ ይ ኾ ኑ ከ ምስ ክ ሮ ች

ሲ ኾ ኑ ከ ምት ወ ዱዋ ቸ ው የ ኾ ኑ ን አ ን ድ

ወ ን ድ ና አ ን ደ ኛ ዋ ስ ት ረ ሳ

አ ን ደ ኛ ይ ቱ ሌ ላ ዋ ን ታ ስ ታውሳ ት

ዘ ን ድ ሁ ለ ት ሴ ቶ ች ይ መስ ክ ሩ

but if two men are not available, then a

man and two women you approve, so

that in case one of them is confused the

other may prompt her

وَ لَا یأَ بَْ الشُّھدََاءُ إ ذِ اَ مَا دُعُوا ምስ ክ ሮ ች ም በ ተ ጠሩ ጊ ዜ እ ን ቢ

አ ይ በ ሉ

When the witnesses are summoned they

should not refuse (to come).

وَلَا تَسْأ مَُوا أ نَْ تَكْتبُُوه صَ غِیرًا أ وَْ

یرًا إ لِىَ أ جََلھِ ◌ِِ كب

ዕ ዳ ው ት ን ሽ ወ ይ ም ት ል ቅ ቢ ኾ ን ም

እ ስ ከ ጊ ዜ ው ድ ረ ስ የ ምት ጽ ፉ ት

ከ መኾ ን አ ት ሰ ል ቹ

But do not neglect to draw up a contract,

big or small, with the time fixed for

paying back the debt

ذَل كُِمْ أ قَ سَْط عِن دَْ للهَّ وَأ قَ وَْمُ ل لِشَّھاَدَة وَأ دَْنَىأ لََّا تَرْتَابُوا

እ ን ዲ ህ ማድ ረ ጋ ች ሁ አ ላ ህ ዘ ን ድ

በ ጣም ት ክ ክ ል ለ ምስ ክ ር ነ ት ም

አ ረ ጋ ጋ ጭ ላ ለ መጠራ ጠራ ች ሁ ም በ ጣም

ቅ ር ብ ነ ው

This is more equitable in the eyes of

God, and better as evidence and best for

avoiding doubt

إ لَِّا أ نَْ تَكُونَ تجَِارَة حَاضِرَة تدُِیرُونَھاَ بیَْنَكُمْ فلَیَْسَ عَلیَْكُمْ جُنَاحٌ أ لََّا

تَكْتبُُوھَا

ግ ን በ መካ ከ ላ ች ሁ እ ጅ በ ጅ

የ ምት ቀ ባ በ ሏ ት ን ግ ድ ብ ት ኾ ን

ባ ት ጽ ፉ ዋ ት በ ና ን ተ ላ ይ ኃ ጢኣ ት

የ ለ ባ ች ሁ ም

But if it is a deal about some

merchandise requiring transaction face

to face, there is no harm if no (contract is

drawn up) in writing.

وَأ شَْھِدُوا إ اَِذ تَباَیعَْتمُ ◌ْ በ ተ ሻ ሻ ጣች ሁም ጊ ዜ አ ስ መስ ክ ሩ Have witnesses to the deal

وَلَا یُضَارَّ كَاتبٌِ وَلَا شَھِید ◌ٌ ጸ ሐፊ ም ምስ ክ ር ም ባ ለ ጉ ዳ ዩ ጋ ር

አ ይ ጎ ዳ ዱ

(and make sure) that the scribe or the

witness is not harmed

ن تَف عَْل وُا فإَ نِھَُّ ف سُُوقٌ ب كُِم ◌ِْْ وَ إ ይ ህ ን ን ብት ሠሩ ም እ ር ሱ በ እ ና ን ተ

የ ሚጠጋ አ መጽ ነ ው

If he is, it would surely be sinful on your

part

وَاتقَّ وُا للهَّ ◌َ አ ላ ህ ን ም ፍ ሩ And have fear of God

وَیُعَل مُِّكُمُ للهَّ ◌ُ አ ላ ህ ም ያ ሳ ውቃች ኋ ል for God gives you knowledge

وَللهَُّ ب كُِلِّ شَيْءٍ عَل یِم ◌ٌ አ ላ ህ ም ነ ገ ሩ ን ሁሉ ዐ ዋ ቂ ነ ው and God is aware of everything

5. AMHARIC-ARABIC NMT

In this work, we adopted openNMT Attention-based Encoder-Decoder architecture, because

attention mechanisms are being progressively used to enhance the performance of NMT by

selectively focusing on sub-parts of the sentence during translation [24]. As described in [25],

”NMT takes a conditional language modeling view of translation by modeling the probability of a

target sentence w1:T given a source sentence x1:S as􀜲( 􀝓􀯧: 􀜶| 􀝔) = Π􀯧

􀬵 􀜲( 􀝓􀯧|􀝓􀬵:􀯧􀬿􀬵, 􀝔) .

This distribution is estimated using an Attention-based Encoder-Decoder architecture”.

62 Computer Science & Information Technology (CS & IT)

Two special kinds of Recurrent Neural Network (RNN) LSTM and GRU which are capable of

learning long-term dependencies are used in this research work. RNN is a type of neural network

for sequential data that can remember its inputs due to an internal memory which is more suited

for machine learning problems. It can produce predictive results in sequential data that the

information cycles through a loop when it makes a decision. It takes into consideration the current

inputs and also previously received inputs, which is learned earlier [26].

LSTM was first introduced by S. Hochreiter and J. Schmidhuber [27], to avoid the long-term

dependency problem. LSTM inherit the exact architecture from standard RNNs, with the

exception of the hidden state. The memory in LSTMs (called cells) takes as input the previous

state and the current input. Internally, these cells decide what to keep in and what to eliminate

from the memory. Then, they combine the previous state, the current memory, and the input.

LSTM calculates a hidden state ht as;

where t, i, f, o, W, U are called the time step, input gate, forget gate, output gate, the recurrent

connection at the previous and current hidden layer, and the weight matrix connecting the inputs

to the current hidden layers respectively. 􀜥􀯧~ is a "candidate" hidden state that is computed based

on the current input and the previous hidden state. C is the internal memory of the unit.

GRU extends LSTM with a gating network generating signals that act to control how the present

input and previous memory work to update the current activation, and thereby the current

network state. Gates are themselves weighted and are selectively updated [28]. For GRU, the

hidden state ht is computed as;

where, ℎ􀯧~ is activation r is a reset gate, and z is an update gate.

Computer Science & Information Technology (CS & IT) 63

Both LSTM and GRU are designed to resolve the vanishing gradient problem which prevents

standard RNNs from learning long-term dependencies through gating mechanism. The general

architecture of LSTM and GRU adopted from [29] [30] is shown in Figure 1.

(a) Long Short-Term memory (b) Gated Recurrent Unit

Figure 1: LSTM and GRU Architecture

A basic form of NMT consists of two components; an encoder which computes a representation

of source sentence S and a decoder which generates one target word at a time and hence

decomposes the conditional probability [24]. The Attention-based Encoder-Decoder architecture

used for Amharic-Arabic NMT is shown in Figure 2.

In general, the proposed model works as follows:

1. Reads the input words one by one to obtain a vector representation from every encoder

time step using LSTM/GRU based encoder

2. Provide the encoder representation to the decoder

3. Extract the output words one by one using another LSTM/GRU based decoder that is

conditioned on the selected inputs from the encoder hidden state of each time step

With this setting, the model is able to selectively focus on useful parts of the input sequence and

hence, learn the alignment (matching segments of original text with their corresponding segments

of the translation).

Figure 2: Attention based Encoder-Decoder architecture for Amharic-Arabic NMT

64 Computer Science & Information Technology (CS & IT)

As shown in Figure 2, Using LSTM Attention based Encoder-Decoder, each word from the

source sentence is associated with a vector wϵRd and will be transformed into [w0, w1, w0, w2,

w3, w4] ϵRdx5 by the encoder, and then an LSTM over this sequence of vectors is computed.

This will be the encoder representation (attention weights) e = [e0, e1, e0, e2, e3, e4]. The

attention weights and word vectors of each time step is fed to another LSTM cell to compute the

context vector which is computed as:

ht = LSTM(ht−1,[wi−1,Ct])

st = g(ht)

pt = softmax(st)

it = argmax(pt)

where, g is a trans-formative function that outputs a vocabulary size vector. A soft-max is then

applied to st to maximize it to a vector of probability pt ϵRV. Each entry of pt will measure how

likely is each word in the vocabulary and the highest probability pt is taken as it = argmax(pt ) ,

corresponding vector of 􀝓􀯜􀳟􀰷􀰭 = 􀝓􀯜􀳟

The vector Ct is attention or context vector which is computed at each decoding step first with the

function f(ht -1, et ′) → αt ′ϵR then a score for each hidden state et ′ of the encoder is computed. The

sequence of αt ′ is normalized using a soft-max and Ct ′ is computed as the weighted average of

et ′. The same procedure is also applied for GRU based NMT

6. EXPERIMENTS AND RESULTS

An OpenNMT system which is an open-source toolkit for NMT is used to construct the NMT

model and translate the text in Amharic to the Arabic language. Preprocessing of both Amharic

and Arabic scripts have a great impact on the performance of the NMT system. Sentences are

split and aligned manually and then all punctuation marks are removed from texts. After

extensive experiments, the maximum source and target sequence length are set to 44, maximum

batch size for training and validation is set to 80 and 40 respectively and learning rate to 0.001

with Adam optimization for both LSTM and GRU RNN type. The remaining parameters are used

as default. The system saves the model for each of 10,000 training samples and then computes

accuracy and perplexity of each model 10 times. Perplexity is a measure of how easily a

probability distribution (the model) predicts the next sequence. A low perplexity indicates that the

translation model is good at predicting/translating the test set.

Computer Science & Information Technology (CS & IT) 65

Table 3 and Table 4 shows LSTM-based and GRU-based NMT evaluation, where, ”Val ppl”,

”Val Acc” ”Av. pred score” and ”Pred ppl” represents Validation Perplexity, Validation

Accuracy, Average Prediction Score and Prediction Perplexity respectively. The result indicate

that LSTM-based NMT outperforms GRU-based NMT. Since this is the first experiment done on

Amharic and Arabic parallel text corpus we consider it as a good performance with small size

corpus.

Table 3. LSTM-based NMT Evaluation

Epoc

hs

BLEUScore

Val.

PPL

Val.

Accuracy

Av. Pred.

Score

Pred.

ppl

1 0.11 12725 33.21 -0.49 1.64

2 0.11 41181.5 33.50 -0.40 1.49

3 0.11 100996 33.64 -0.35 1.41

4 0.12 100417 34.34 -0.34 1.40

5 0.12 99881.1 34.32 -0.34 1.40

6 0.12 99876.1 34.33 -0.34 1.40

7 0.12 99876 34.33 -0.34 1.40

8 0.12 99876 34.33 -0.34 1.40

9 0.12 99876 34.33 -0.34 1.40

10 0.12 99876 34.33 -0.34 1.4

Table 4. GRU-based NMT Evaluation

Epoc

hs

BLEUScore

Val.

PPL

Val.

Accuracy

Av. Pred.

Score

Pred.

ppl

1 0.108 13647 32.65 -0.51 1.66

2 0.101 65598.4 32.68 -0.39 1.48

3 0.098 172950 32.38 -0.35 1.43

4 0.105 173231 33.10 -0.34 1.40

5 0.105 175635 33.12 -0.34 1.40

6 0.105 175701 33.11 -0.34 1.40

7 0.105 175702 33.11 -0.34 1.40

8 0.105 175702 33.11 -0.34 1.40

9 0.105 175702 33.11 -0.34 1.40

10 0.105 175702 33.11 -0.34 1.40

The models are evaluated using Bilingual Evaluation Understudy (BLEU). BLEU is a score for

comparing a candidate translation of the text with reference translations. The primary

programming task for a BLEU implementer is to compare n-grams of the candidate with the ngrams

of the reference translation and count the number of matches. These matches are positionindependent.

More the matches, better the candidate translation is. BLEU is inexpensive to

calculate and it is quick to use. It is expressed as the following equation [31];

where pn is an n-gram precision that uses n-grams up to length N and positive weights wn that

sum to one.We also compared the two recurrent units LSTM and GRU based OpenNMT

translation algorithm with Google Translation System which is a free multilingual translation

system developed by Google to translate multilingual text [6] and the results are shown in Figure

3. LSTM based OpenNMT outperforms over GRU based OpenNMT and Google Translation

system, which is BLEU score of 12%, 11%, and 6% respectively.

66 Computer Science & Information Technology (CS & IT)

Figure 3: Best BLEU-Scores of LSTM and GRU based OpenNMT translation and Google

Translation System

7. CONCLUSION

Many researchers have investigated to solve translation problems for many language pairs and

NMT has recently shown promising results on multiple language pairs. However, much of the

research on this area has focused on European languages despite these languages being very rich

in resources. Since Amharic and Arabic languages lack parallel corpus for the purpose of

developing NMT, small size Amharic-Arabic parallel text corpora have been constructed to train

the Amharic to Arabic NMT system by splitting the verses manually into separate sentences of

Amharic language as a source sentence and Arabic language as a target sentence. Using the

constructed corpus LSTM-based and GRU-based NMT models are developed and evaluated

using BLEU. The results are also compared with Google Translation system. Since this is the first

experiment done on Amharic and Arabic parallel text corpus, we consider it as a good

performance for small size corpus. Extensive experiments with a large amount of training data

could be implemented for better performance.

REFERENCES

[1] R. Mitkov, The Oxford handbook of computational linguistics. Oxford University Press, 2004.

[2] B. Maylath, “Current trends in translation,” Commun. Lang. Work, vol. 2, no. 2, pp. 41–50, 2013.

[3] J. Oladosu, A. Esan, I. Adeyanju, B. Adegoke, O. Olaniyan, and B. Omodunbi, “Approaches to

Machine Translation: A Review,” FUOYE J. Eng. Technol., vol. 1, pp. 120–126, 2016.

[4] MemoQ, “5 Translation Technology Trends to Watch Out for in 2019,” 2019. [Online]. Available:

https://slator.com/press-releases/5-translation-technology-trends-to-watch-out-in-2019/.

[5] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, p. 436, 2015.

[6] Y. Wu et al., “Google’s neural machine translation system: Bridging the gap between human and

machine translation,” arXiv Prepr. arXiv1609.08144, 2016.

[7] S. Islam, A. Paul, B. S. Purkayastha, and I. Hussain, “CONSTRUCTION OF ENGLISH-BODO

PARALLEL TEXT CORPUS FOR STATISTICAL MACHINE TRANSLATION,” Int. J. Nat. Lang.

Comput. Vol, vol. 7, 2018.

[8] H. L. Shashirekha and I. Gashaw, “DICTIONARY BASED AMHARIC-ARABIC CROSS

LANGUAGE INFORMATION RETRIEVAL,” Comput. Sci. \& Inf. Technol., vol. 6, pp. 49–60,

2016.

[9] P. Koehn and R. Knowles, “Six challenges for neural machine translation,” arXiv Prepr.

arXiv1706.03872, 2017.

Computer Science & Information Technology (CS & IT) 67

[10] Gezmu Andargachew Mekonnen Andreas Nurnberger and T. B. Bati, “A Parallel Corpus for

Amharic-English Machine Translation,” 2018.

[11] S. M. Strassel and J. Tracey, “LORELEI Language Packs: Data, Tools, and Resources for

Technology Development in Low Resource Languages.,” in LREC, 2016.

[12] M. M. Sakre, M. M. Kouta, and A. M. N. Allam, “automated construction of Arabic-English parallel

corpus,” J. Adv. Comput. Sci., vol. 3, 2009.

[13] A. A.-S. Ahmad, B. Hammo, and S. Yagi, “ENGLISH-ARABIC POLITICAL PARALLEL

CORPUS: CONSTRUCTION, ANALYSIS AND A CASE STUDY IN TRANSLATION

STRATEGIES,” Jordanian J. Comput. Inf. Technol., vol. 3, no. 3, 2017.

[14] G. Inoue, N. Habash, Y. Matsumoto, and H. Aoyama, “A Parallel Corpus of Arabic-Japanese News

Articles,” in Proceedings of the Eleventh International Conference on Language Resources and

Evaluation (LREC-2018), 2018.

[15] H. M. Alotaibi, “Arabic-English Parallel Corpus: A New Resource for Translation Training and

Language Teaching,” Arab World English J. Vol., vol. 8, 2017.

[16] P. Resnik and N. A. Smith, “The web as a parallel corpus,” Comput. Linguist., vol. 29, no. 3, pp. 349–

380, 2003.

[17] K. Cho et al., “Learning phrase representations using RNN encoder-decoder for statistical machine

translation,” arXiv Prepr. arXiv1406.1078, vol. 3, 2014.

[18] D. Bahdanau, K. Cho, and Y. Bengio, “Neural machine translation by jointly learning to align and

translate,” arXiv Prepr. arXiv1409.0473, vol. 7, 2014.

[19] A. Almahairi, K. Cho, N. Habash, and A. Courville, “First result on Arabic neural machine

translation,” arXiv Prepr. arXiv1606.02680, vol. 1, 2016.

[20] M. Wordofa, “Semantic Indexing and Document Clustering for Amharic Information Retrieval,”

AAU, 2013.

[21] M. El-Haj, “Multi-document arabic text summarisation,” University of Essex, 2012.

[22] L. Rura, W. Vandeweghe, and M. Montero Perez, “Designing a parallel corpus as a multifunctional

translator’s aid,” in XVIII FIT World Congress= XVIIIe Congrès mondial de la FIT, 2008.

[23] J. Tiedemann, “Parallel Data, Tools and Interfaces in OPUS.,” in Lrec, 2012, vol. 2012, pp. 2214–

2218.

[24] M.-T. Luong, H. Pham, and C. D. Manning, “Effective approaches to attention-based neural machine

translation,” arXiv Prepr. arXiv1508.04025, 2015.

[25] G. Klein, Y. Kim, Y. Deng, J. Senellart, and A. M. Rush, “Opennmt: Open-source toolkit for neural

machine translation,” arXiv Prepr. arXiv1701.02810, 2017.

[26] N. Donges, “Recurrent Neural Networks and LSTM,” 2018. [Online]. Available:

https://towardsdatascience.com/recurrent-neural-networks-and-lstm-4b601dd822a5.

[27] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Comput., vol. 9, no. 8, pp.

1735–1780, 1997.

[28] J. Chung, C. Gulcehre, K. Cho, and Y. Bengio, “Empirical evaluation of gated recurrent neural

networks on sequence modeling,” arXiv Prepr. arXiv1412.3555, 2014.

68 Computer Science & Information Technology (CS & IT)

[29] A. Graves, “Generating sequences with recurrent neural networks,” arXiv Prepr. arXiv1308.0850,

2013.

[30] S. Du, T. Li, X. Gong, Z. Yu, Y. Huang, and S.-J. Horng, “A hybrid method for traffic flow

forecasting using multimodal deep learning,” arXiv Prepr. arXiv1803.02099, 2018.

[31] K. Wolk and K. Marasek, “Neural-based machine translation for medical text domain. Based on

European Medicines Agency leaflet texts,” Procedia Comput. Sci., vol. 64, pp. 2–9, 2015.

AUTHORS

Ibrahim Gashaw Kassa is a Ph.D. candidate at Mangalore University

Karnataka State, India, since 2016. He graduated in 2006 in Information System

from Addis Ababa University, Ethiopia. In 2014, he obtained his master’s

degree in Information Technology from the University of Gondar, Ethiopia., and

he serves as a lecturer at the University of Gondar from 2009 to May 2016. His

research interest is in Cross-Language Information Retrieval, Machine

translation Artificial Intelligence Natural Language Processing

Dr. H L Shashirekha is a Professor in the Department of Computer Science,

Mangalore University, Mangalore, Karnataka State, India. She completed her

M.Sc. in Computer Science in 1992 and Ph.D. in 2010 from University of

Mysore. She is a member of Board of Studies and Board of Examiners (PG) in

Computer Science, Mangalore University. She has several papers in

International Conferences and published several papers in International Journals

and Conference Proceedings. Her area of research includes Text Mining and

Natural Language Processing.

Welcome Corps

Refugees are individuals outside of the United States who have been forced to flee their home countries due to persecution or a fear of persecution based on race, religion, nationality, membership in a particular social group, or political opinion. They often live in refugee camps and cities outside of their home countries until they can either return home, locally integrate within the country to which they fled, or be permanently resettled to a third country like the United States.

 

IRS issues guidance on state tax payments to help taxpayer

IR-2023-23, Feb. 10, 2023

WASHINGTON — The Internal Revenue Service provided details today clarifying the federal tax status involving special payments made by 21 states in 2022.

The IRS has determined that in the interest of sound tax administration and other factors, taxpayers in many states will not need to report these payments on their 2022 tax returns.

During a review, the IRS determined it will not challenge the taxability of payments related to general welfare and disaster relief. This means that people in the following states do not need to report these state payments on their 2022 tax return: California, Colorado, Connecticut, Delaware, Florida, Hawaii, Idaho, Illinois, Indiana, Maine, New Jersey, New Mexico, New York, Oregon, Pennsylvania and Rhode Island. Alaska is in this group as well, but please see below for more nuanced information.

In addition, many people in Georgia, Massachusetts, South Carolina and Virginia also will not include state payments in income for federal tax purposes if they meet certain requirements. For these individuals, state payments will not be included for federal tax purposes if the payment is a refund of state taxes paid and either the recipient claimed the standard deduction or itemized their deductions but did not receive a tax benefit.

The IRS appreciates the patience of taxpayers, tax professionals, software companies and state tax administrators as the IRS and Treasury worked to resolve this unique and complex situation.

The IRS is aware of questions involving special tax refunds or payments made by certain states related to the pandemic and its associated consequences in 2022. A variety of state programs distributed these payments in 2022 and the rules surrounding their treatment for federal income tax purposes are complex. While in general payments made by states are includable in income for federal tax purposes, there are exceptions that would apply to many of the payments made by states in 2022.

To assist taxpayers who have received these payments file their returns in a timely fashion, the IRS is providing the additional information below.

Refund of state taxes paid

If the payment is a refund of state taxes paid and either the recipient claimed the standard deduction or itemized their deductions but did not receive a tax benefit (for example, because the $10,000 tax deduction limit applied) the payment is not included in income for federal tax purposes.

Payments from the following states in 2022 fall in this category and will be excluded from income for federal tax purposes unless the recipient received a tax benefit in the year the taxes were deducted.

• Georgia
• Massachusetts
• South Carolina
• Virginia

General welfare and disaster relief payments

If a payment is made for the promotion of the general welfare or as a disaster relief payment, for example related to the outgoing pandemic, it may be excludable from income for federal tax purposes under the General Welfare Doctrine or as a Qualified Disaster Relief Payment. Determining whether payments qualify for these exceptions is a complex fact intensive inquiry that depends on a number of considerations.

The IRS has reviewed the types of payments made by various states in 2022 that may fall in these categories and given the complicated fact-specific nature of determining the treatment of these payments for federal tax purposes balanced against the need to provide certainty and clarity for individuals who are now attempting to file their federal income tax returns, the IRS has determined that in the best interest of sound tax administration and given the fact that the pandemic emergency declaration is ending in May, 2023 making this an issue only for the 2022 tax year, if a taxpayer does not include the amount of one of these payments in its 2022 income for federal income tax purposes, the IRS will not challenge the treatment of the 2022 payment as excludable for income on an original or amended return.

Payments from the following states fall in this category and the IRS will not challenge the treatment of these payments as excludable for federal income tax purposes in 2022.

• Alaska ^[1]
• California
• Colorado
• Connecticut
• Delaware
• Florida
• Hawaii
• Idaho
• Illinois ^[2]
• Indiana
• Maine
• New Jersey
• New Mexico
• New York2
• Oregon
• Pennsylvania
• Rhode Island

For a list of the specific payments to which this applies, please see this chart.

Other payments

Other payments that may have been made by states are generally includable in income for federal income tax purposes. This includes the annual payment of Alaska's Permanent Fund Dividend and any payments from states provided as compensation to workers.

10 best businesses immigrants can start in American

10 best businesses immigrants can start in American easly 

1. Food Truck Business: Food trucks are a popular business venture and can be easily started with a minimal investment. The business involves selling pre-packaged food items, such as sandwiches, hot dogs, and tacos, from a mobile truck. An immigrant can easily open a food truck business by purchasing a vehicle, stocking it with food items, obtaining a business license, and adhering to local health codes. Starting a food truck business requires a small staff and can be operated with a minimal overhead. 

 2. Home Cleaning Business: Home cleaning is a great business to start with minimal investment and low overhead. With the proper licensing and insurance, an immigrant can offer cleaning services to residential clients. Cleaning services can include vacuuming, dusting, mopping, and window cleaning. 

 3. Event Planning Business: An immigrant can start a profitable event planning business with minimal investment. The business involves helping clients plan and organize events, such as weddings, birthdays, baby showers, anniversaries, and corporate events. An immigrant can use their creativity and organizational skills to create memorable events for their clients. 

 4. Online Tutoring Business: An immigrant can start an online tutoring business with a minimal investment. The business involves providing tutoring services to students in areas such as math, science, English, and foreign languages. An immigrant can use their knowledge and experience to help students succeed in their studies. 

 5. Pet Sitting Business: An immigrant can start a pet sitting business with minimal investment. The business involves providing pet care services such as walking, feeding, grooming, and playing with pets while their owners are away. An immigrant can use their love of animals to build a successful pet sitting business. 

 6. Home Repair Business: An immigrant can start a home repair business with a minimal investment. The business involves providing services such as plumbing, electrical, carpentry, and appliance repair. An immigrant can use their knowledge and experience to help homeowners keep their homes in good condition. 

 7. Online Store: An immigrant can start an online store with minimal investment. The business involves selling products such as clothing, jewelry, electronics, and home goods. An immigrant can use their knowledge of e-commerce to build a successful online store. 

 8. Home Decorating Business: An immigrant can start a home decorating business with minimal investment. The business involves helping clients choose the perfect colors, fabrics, furniture, and accessories to create a beautiful living space. An immigrant can use their creativity and eye for design to create stunning home decor for their clients. 

 9. Personal Shopping Business: An immigrant can start a personal shopping business with minimal investment. The business involves helping clients find the perfect items for their lifestyle. An immigrant can use their knowledge of fashion and style to help clients look their best. 

 10. Landscaping Business: An immigrant can start a landscaping business with minimal investment. The business involves designing and maintaining outdoor spaces such as gardens, patios, and yards. An immigrant can use their knowledge of plants, flowers, and trees to create beautiful outdoor spaces for their clients.

How to start Chicken Farming

 

Chapter 1: Introduction to Chicken Farming

Chicken farming is a growing industry that provides an opportunity for individuals to produce fresh, high-quality eggs and meat, reduce food waste, and create a source of income. Whether you are a beginner or an experienced farmer, there is always a place for you in the world of chicken farming. In this chapter, we will provide an overview of the benefits of starting a chicken farm, the chicken farming industry, and the types of chicken farms that exist.