{"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/option-comparison-network-for-multiple-choice","title":"Option Comparison Network for Multiple-choice Reading Comprehension","arxiv_id":"1903.03033","date":"2019-03-07","proceeding":null,"authors":["Qiu Ran","Peng Li","Weiwei Hu","Jie zhou"],"abstract":"Multiple-choice reading comprehension (MCRC) is the task of selecting the\ncorrect answer from multiple options given a question and an article. Existing\nMCRC models typically either read each option independently or compute a\nfixed-length representation for each option before comparing them. However,\nhumans typically compare the options at multiple-granularity level before\nreading the article in detail to make reasoning more efficient. Mimicking\nhumans, we propose an option comparison network (OCN) for MCRC which compares\noptions at word-level to better identify their correlations to help reasoning.\nSpecially, each option is encoded into a vector sequence using a skimmer to\nretain fine-grained information as much as possible. An attention mechanism is\nleveraged to compare these sequences vector-by-vector to identify more subtle\ncorrelations between options, which is potentially valuable for reasoning.\nExperimental results on the human English exam MCRC dataset RACE show that our\nmodel outperforms existing methods significantly. Moreover, it is also the\nfirst model that surpasses Amazon Mechanical Turker performance on the whole\ndataset.","url_abs":"http://arxiv.org/abs/1903.03033v1","url_pdf":"http://arxiv.org/pdf/1903.03033v1.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":[],"tasks":[{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-race","task":"Question Answering","dataset":"RACE","model":"OCN_large","rank_in_archive_order":2,"of":7,"metrics":{"RACE":"71.7","RACE-h":"69.6","RACE-m":"76.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.03033","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}