Summary of Building a Rich Dataset to Empower the Persian Question Answering Systems, by Mohsen Yazdinejad et al.
Building a Rich Dataset to Empower the Persian Question Answering Systems
by Mohsen Yazdinejad, Marjan Kaedi
First submitted to arxiv on: 28 Dec 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 The paper presents NextQuAD, a comprehensive open-domain dataset for Persian question answering. The dataset consists of 7,515 contexts, including 23,918 questions and answers. A BERT-based question answering model is applied to this dataset using two pre-trained language models, ParsBERT and XLM-RoBERTa. The results are ensemble using mean logits. The model achieves an Exact Match (EM) score of 0.95 on the development set and a F1-score of 0.97. To compare NextQuAD with other Persian datasets, the trained model is evaluated on PersianQA and ParSQuAD, showing improvements in EM scores. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a big dataset for answering questions in Persian, which can help computers understand this language better. They test their method using two computer models, ParsBERT and XLM-RoBERTa, and get good results. The dataset is compared to other similar datasets, and it does even better. |
Keywords
» Artificial intelligence » Bert » F1 score » Logits » Question answering
