{"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/subword-augmented-embedding-for-cloze-reading","title":"Subword-augmented Embedding for Cloze Reading Comprehension","arxiv_id":"1806.09103","date":"2018-06-24","proceeding":"COLING 2018 8","authors":["Zhuosheng Zhang","Yafang Huang","Hai Zhao"],"abstract":"Representation learning is the foundation of machine reading comprehension.\nIn state-of-the-art models, deep learning methods broadly use word and\ncharacter level representations. However, character is not naturally the\nminimal linguistic unit. In addition, with a simple concatenation of character\nand word embedding, previous models actually give suboptimal solution. In this\npaper, we propose to use subword rather than character for word embedding\nenhancement. We also empirically explore different augmentation strategies on\nsubword-augmented embedding to enhance the cloze-style reading comprehension\nmodel reader. In detail, we present a reader that uses subword-level\nrepresentation to augment word embedding with a short list to handle rare words\neffectively. A thorough examination is conducted to evaluate the comprehensive\nperformance and generalization ability of the proposed reader. Experimental\nresults show that the proposed approach helps the reader significantly\noutperform the state-of-the-art baselines on various public datasets.","url_abs":"http://arxiv.org/abs/1806.09103v1","url_pdf":"http://arxiv.org/pdf/1806.09103v1.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":"subword-augmented-embedding-for-cloze-reading","repo_url":"https://github.com/cooelf/subMrc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-reading-comprehension","task_name":"Machine Reading Comprehension"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}