Summary of Uqa: Corpus For Urdu Question Answering, by Samee Arif et al.
UQA: Corpus for Urdu Question Answering
by Samee Arif, Sualeha Farid, Awais Athar, Agha Ali Raza
First submitted to arxiv on: 2 May 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper introduces UQA, a novel dataset for question answering and text comprehension in Urdu. The dataset is generated by translating the Stanford Question Answering Dataset (SQuAD2.0) using a technique called EATS. The paper evaluates two translation models – Google Translator and Seamless M4T – and benchmarks several multilingual QA models, including mBERT, XLM-RoBERTa, and mT5, on UQA. The results show promising performances, with an F1 score of 85.99 and 74.56 EM for XLM-RoBERTa-XL. The paper highlights the value of UQA as a resource for developing multilingual NLP systems for Urdu and enhancing cross-lingual transferability. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary UQA is a new dataset for asking questions and understanding text in Urdu, a language spoken by over 70 million people. To create this dataset, researchers translated a big English question answering dataset called SQuAD2.0 using a special technique that keeps the answer spans in context. They tested two translation models and found that one worked better than the other. Then, they used these models to test some of the best multilingual language processing models on UQA. The results are promising and show that this dataset can be useful for developing language processing systems for Urdu and other languages. |
Keywords
» Artificial intelligence » F1 score » Nlp » Question answering » Transferability » Translation
