{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/generating-distractors-for-reading","title":"Generating Distractors for Reading Comprehension Questions from Real Examinations","arxiv_id":"1809.02768","date":"2018-09-08","proceeding":null,"authors":["Yifan Gao","Lidong Bing","Piji Li","Irwin King","Michael R. Lyu"],"abstract":"We investigate the task of distractor generation for multiple choice reading\ncomprehension questions from examinations. In contrast to all previous works,\nwe do not aim at preparing words or short phrases distractors, instead, we\nendeavor to generate longer and semantic-rich distractors which are closer to\ndistractors in real reading comprehension from examinations. Taking a reading\ncomprehension article, a pair of question and its correct option as input, our\ngoal is to generate several distractors which are somehow related to the\nanswer, consistent with the semantic context of the question and have some\ntrace in the article. We propose a hierarchical encoder-decoder framework with\nstatic and dynamic attention mechanisms to tackle this task. Specifically, the\ndynamic attention can combine sentence-level and word-level attention varying\nat each recurrent time step to generate a more readable sequence. The static\nattention is to modulate the dynamic attention not to focus on question\nirrelevant sentences or sentences which contribute to the correct option. Our\nproposed framework outperforms several strong baselines on the first prepared\ndistractor generation dataset of real reading comprehension questions. For\nhuman evaluation, compared with those distractors generated by baselines, our\ngenerated distractors are more functional to confuse the annotators.","url_abs":"http://arxiv.org/abs/1809.02768v2","url_pdf":"http://arxiv.org/pdf/1809.02768v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"generating-distractors-for-reading","repo_url":"https://github.com/Evan-Gao/Distractor-Generation-RACE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"generating-distractors-for-reading","repo_url":"https://github.com/Yifan-Gao/Distractor-Generation-RACE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"distractor-generation","task_name":"Distractor Generation"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.02768","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}