Skip to content

Instructing Generative Models for the Task of Arabic Question Answering

License

Notifications You must be signed in to change notification settings

zainmujahid/Arabic-QnA-LLMs

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 

Repository files navigation

Arabic-QnA-LLMs

NLP702 Project - Instructing Generative Models for the Task of Arabic Question Answering (Code to be Uploaded)

This course project focuses on evaluating dif- ferent models for question answering in Ara- bic, specifically using AraGPT2 and mGPT as the models for evaluation. The project em- ploys manual evaluation, following a similar approach as the self-instruct paper, to rank the quality of the models’ output. The evaluation aims to assess the performance of AraGPT2 and mGPT in generating accurate and contex- tually relevant answers to questions in Arabic. The results of the evaluation will provide in- sights into the strengths and weaknesses of these models for question answering in Ara- bic, and contribute to the body of knowledge in natural language processing and Arabic lan- guage processing.

About

Instructing Generative Models for the Task of Arabic Question Answering

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published