{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:17:14Z","timestamp":1750220234754,"version":"3.41.0"},"reference-count":37,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2022,1,19]],"date-time":"2022-01-19T00:00:00Z","timestamp":1642550400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61976072 and 61772153"],"award-info":[{"award-number":["61976072 and 61772153"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2022,7,31]]},"abstract":"<jats:p>\n            Owing to the availability of various large-scale\n            <jats:bold>Machine Reading Comprehension<\/jats:bold>\n            (\n            <jats:bold>MRC<\/jats:bold>\n            ) datasets, building an effective model to extract passage spans for question answering has been well studied in previous works. However, in reality, there are some questions that cannot be answered through the passage information, which brings more challenges to this task. In this article, we propose an\n            <jats:bold>Interactive Gated Decoder<\/jats:bold>\n            (\n            <jats:bold>IG Decoder<\/jats:bold>\n            ), which focuses on modeling the interactions between the answer span prediction and no-answer prediction with a gating mechanism. We also propose a simple but effective approach for automatically generating pseudo training data, which aims to enrich the training data of the unanswerable questions. Experimental results on popular benchmark SQuAD 2.0 and NewsQA show that the proposed approaches yield consistent improvements over traditional BERT-large and strong ALBERT-xxlarge baseline systems. We also provide detailed ablations of the proposed method and error analysis on hard samples, which could be helpful in future research.\n          <\/jats:p>","DOI":"10.1145\/3501399","type":"journal-article","created":{"date-parts":[[2022,1,19]],"date-time":"2022-01-19T20:19:23Z","timestamp":1642623563000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Interactive Gated Decoder for Machine Reading Comprehension"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2452-375X","authenticated-orcid":false,"given":"Yiming","family":"Cui","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Beijing, China"}]},{"given":"Wanxiang","family":"Che","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Beijing, China"}]},{"given":"Ziqing","family":"Yang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Cognitive Intelligence, Beijing, China"}]},{"given":"Ting","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Beijing, China"}]},{"given":"Bing","family":"Qin","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Beijing, China"}]},{"given":"Shijin","family":"Wang","sequence":"additional","affiliation":[{"name":"iFLYTEK AI Research, Hefei, China"}]},{"given":"Guoping","family":"Hu","sequence":"additional","affiliation":[{"name":"iFLYTEK AI Research, Hefei, China"}]}],"member":"320","published-online":{"date-parts":[[2022,1,19]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.5555\/3026877.3026899"},{"key":"e_1_3_2_3_2","article-title":"Layer normalization","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E. Hinton. 2016. Layer normalization. arXiv:1607.06450.","journal-title":"arXiv:1607.06450"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1171"},{"key":"e_1_3_2_5_2","volume-title":"ICLR","author":"Clark Kevin","year":"2020","unstructured":"Kevin Clark, Minh-Thang Luong, Quoc V. Le, and Christopher D. Manning. 2020. ELECTRA: Pre-training text encoders as discriminators rather than generators. In ICLR. https:\/\/openreview.net\/pdf?id=r1xMH1BtvB."},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1055"},{"key":"e_1_3_2_7_2","first-page":"1777","volume-title":"Proceedings of the 26th International Conference on Computational Linguistics: Technical Papers (COLING\u201916)","author":"Cui Yiming","year":"2016","unstructured":"Yiming Cui, Ting Liu, Zhipeng Chen, Shijin Wang, and Guoping Hu. 2016. Consensus attention-based neural networks for Chinese reading comprehension. In Proceedings of the 26th International Conference on Computational Linguistics: Technical Papers (COLING\u201916). The COLING 2016 Organizing Committee, 1777\u20131786. http:\/\/aclweb.org\/anthology\/C16-1167."},{"key":"e_1_3_2_8_2","article-title":"Contextual recurrent units for cloze-style reading comprehension","author":"Cui Yiming","year":"2019","unstructured":"Yiming Cui, Wei-Nan Zhang, Wanxiang Che, Ting Liu, Zhipeng Chen, Shijin Wang, and Guoping Hu. 2019. Contextual recurrent units for cloze-style reading comprehension. arXiv:1911.05960.","journal-title":"arXiv:1911.05960"},{"key":"e_1_3_2_9_2","first-page":"4171","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, 4171\u20134186."},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1168"},{"key":"e_1_3_2_11_2","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Gaussian error linear units (GELUs). arXiv:1606.08415.","journal-title":"arXiv:1606.08415"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969428"},{"key":"e_1_3_2_13_2","article-title":"The Goldilocks principle: Reading children\u2019s books with explicit memory representations","author":"Hill Felix","year":"2015","unstructured":"Felix Hill, Antoine Bordes, Sumit Chopra, and Jason Weston. 2015. The Goldilocks principle: Reading children\u2019s books with explicit memory representations. arXiv:1511.02301.","journal-title":"arXiv:1511.02301"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016529"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1086"},{"key":"e_1_3_2_16_2","article-title":"Adam: A method for stochastic optimization","author":"Kingma Diederik","year":"2014","unstructured":"Diederik Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980.","journal-title":"arXiv:1412.6980"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.5555\/3504035.3504750"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1082"},{"key":"e_1_3_2_19_2","volume-title":"International Conference on Learning Representations (ICLR\u201919)","author":"Lan Zhenzhong","year":"2019","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2019. ALBERT: A lite BERT for self-supervised learning of language representations. In International Conference on Learning Representations (ICLR\u201919). https:\/\/openreview.net\/forum?id=H1eA7AEtvS."},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K17-1034"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1010"},{"key":"e_1_3_2_22_2","article-title":"Stochastic answer networks for SQuAD 2.0","author":"Liu Xiaodong","year":"2018","unstructured":"Xiaodong Liu, Wei Li, Yuwei Fang, Aerin Kim, Kevin Duh, and Jianfeng Gao. 2018. Stochastic answer networks for SQuAD 2.0. arXiv:1809.09194.","journal-title":"arXiv:1809.09194"},{"key":"e_1_3_2_23_2","article-title":"Roberta: A robustly optimized BERT pretraining approach","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized BERT pretraining approach. arXiv:1907.11692.","journal-title":"arXiv:1907.11692"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2124"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_3_2_26_2","first-page":"193","volume-title":"Proceedings of EMNLP 2013","author":"Richardson Matthew","year":"2013","unstructured":"Matthew Richardson, Christopher J. C. Burges, and Erin Renshaw. 2013. MCTest: A challenge dataset for the open-domain machine comprehension of text. In Proceedings of EMNLP 2013. 193\u2013203."},{"key":"e_1_3_2_27_2","volume-title":"International Conference on Learning Representations (ICLR\u201917)","author":"Seo Minjoon","year":"2017","unstructured":"Minjoon Seo, Aniruddha Kembhavi, Ali Farhadi, and Hananneh Hajishirzi. 2017. Bi-Directional attention flow for machine comprehension. In International Conference on Learning Representations (ICLR\u201917). https:\/\/openreview.net\/forum?id=HJ0UKP9ge."},{"key":"e_1_3_2_28_2","article-title":"U-Net: Machine reading comprehension with unanswerable questions","author":"Sun Fu","year":"2018","unstructured":"Fu Sun, Linyang Li, Xipeng Qiu, and Yang Liu. 2018. U-Net: Machine reading comprehension with unanswerable questions. arXiv:1810.06638.","journal-title":"arXiv:1810.06638"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.5555\/3327345.3327399"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2623"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.5555\/2969442.2969540"},{"key":"e_1_3_2_33_2","article-title":"Machine comprehension using match-LSTM and answer pointer","author":"Wang Shuohang","year":"2016","unstructured":"Shuohang Wang and Jing Jiang. 2016. Machine comprehension using match-LSTM and answer pointer. arXiv:1608.07905.","journal-title":"arXiv:1608.07905"},{"key":"e_1_3_2_34_2","article-title":"Dynamic coattention networks for question answering","author":"Xiong Caiming","year":"2016","unstructured":"Caiming Xiong, Victor Zhong, and Richard Socher. 2016. Dynamic coattention networks for question answering. arXiv:1611.01604.","journal-title":"arXiv:1611.01604"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454804"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6510"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6511"},{"key":"e_1_3_2_38_2","unstructured":"Zhuosheng Zhang Junjie Yang and Hai Zhao. 2020. Retrospective reader for machine reading comprehension. arXiv:2001.09694."}],"container-title":["ACM Transactions on Asian and Low-Resource Language Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3501399","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3501399","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:20Z","timestamp":1750188620000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3501399"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,19]]},"references-count":37,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,7,31]]}},"alternative-id":["10.1145\/3501399"],"URL":"https:\/\/doi.org\/10.1145\/3501399","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"type":"print","value":"2375-4699"},{"type":"electronic","value":"2375-4702"}],"subject":[],"published":{"date-parts":[[2022,1,19]]},"assertion":[{"value":"2021-02-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-01-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}