{"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/dream-a-challenge-dataset-and-models-for","title":"DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension","arxiv_id":"1902.00164","date":"2019-02-01","proceeding":null,"authors":["Kai Sun","Dian Yu","Jianshu Chen","Dong Yu","Yejin Choi","Claire Cardie"],"abstract":"We present DREAM, the first dialogue-based multiple-choice reading\ncomprehension dataset. Collected from English-as-a-foreign-language\nexaminations designed by human experts to evaluate the comprehension level of\nChinese learners of English, our dataset contains 10,197 multiple-choice\nquestions for 6,444 dialogues. In contrast to existing reading comprehension\ndatasets, DREAM is the first to focus on in-depth multi-turn multi-party\ndialogue understanding. DREAM is likely to present significant challenges for\nexisting reading comprehension systems: 84% of answers are non-extractive, 85%\nof questions require reasoning beyond a single sentence, and 34% of questions\nalso involve commonsense knowledge.\n  We apply several popular neural reading comprehension models that primarily\nexploit surface information within the text and find them to, at best, just\nbarely outperform a rule-based approach. We next investigate the effects of\nincorporating dialogue structure and different kinds of general world knowledge\ninto both rule-based and (neural and non-neural) machine learning-based reading\ncomprehension models. Experimental results on the DREAM dataset show the\neffectiveness of dialogue structure and general world knowledge. DREAM will be\navailable at https://dataset.org/dream/.","url_abs":"http://arxiv.org/abs/1902.00164v1","url_pdf":"http://arxiv.org/pdf/1902.00164v1.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":"dream-a-challenge-dataset-and-models-for","repo_url":"https://github.com/nlpdata/dream","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"dialogue-understanding","task_name":"Dialogue Understanding"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"world-knowledge","task_name":"World Knowledge"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1902.00164","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}