{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T20:57:40Z","timestamp":1730321860551,"version":"3.28.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,11,8]]},"DOI":"10.1145\/3373419.3373430","type":"proceedings-article","created":{"date-parts":[[2020,1,24]],"date-time":"2020-01-24T05:52:56Z","timestamp":1579845176000},"page":"170-174","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Head Bidirectional Attention for MRC"],"prefix":"10.1145","author":[{"given":"Dagmawi","family":"Moges","sequence":"first","affiliation":[{"name":"UESTC, Chengdu, China"}]},{"given":"Hong","family":"Qu","sequence":"additional","affiliation":[{"name":"UESTC, Chengdu, China"}]},{"given":"Mingsheng","family":"Fu","sequence":"additional","affiliation":[{"name":"UESTC, Chengdu, China"}]}],"member":"320","published-online":{"date-parts":[[2020,1,24]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text,\" in Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","author":"Rajpurkar P.","year":"2016","unstructured":"P. Rajpurkar , J. Zhang , K. Lopyrev , and P. Liang , \" SQuAD: 100,000+ Questions for Machine Comprehension of Text,\" in Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing , 2016 . P. Rajpurkar, J. Zhang, K. Lopyrev, and P. Liang, \"SQuAD: 100,000+ Questions for Machine Comprehension of Text,\" in Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 2016."},{"key":"e_1_3_2_1_2_1","volume-title":"WikiQA: A Challenge Dataset for Open-Domain Question Answering","author":"Yang Y.","year":"2015","unstructured":"Y. Yang , W. Yih , and C. Meek , \" WikiQA: A Challenge Dataset for Open-Domain Question Answering ,\" 2015 . Y. Yang, W. Yih, and C. Meek, \"WikiQA: A Challenge Dataset for Open-Domain Question Answering,\" 2015."},{"key":"e_1_3_2_1_3_1","volume-title":"MS MARCO: A human generated MAchine reading COmprehension dataset,\" in CEUR Workshop Proceedings","author":"T. Nguyen","year":"2016","unstructured":"T. Nguyen et al. , \" MS MARCO: A human generated MAchine reading COmprehension dataset,\" in CEUR Workshop Proceedings , 2016 . T. Nguyen et al., \"MS MARCO: A human generated MAchine reading COmprehension dataset,\" in CEUR Workshop Proceedings, 2016."},{"key":"e_1_3_2_1_4_1","volume-title":"arXiv1906.08237","author":"Yang Q. V","year":"2019","unstructured":"Q. V Yang , Zhilin and Dai , Zihang and Yang , Yiming and Carbonell , Jaime and Salakhutdinov , Ruslan and Le , \" Generalized Autoregressive Pretraining for Language Understanding ,\" ar Xiv Prepr . arXiv1906.08237 , 2019 . Q. V Yang, Zhilin and Dai, Zihang and Yang, Yiming and Carbonell, Jaime and Salakhutdinov, Ruslan and Le, \"Generalized Autoregressive Pretraining for Language Understanding,\" arXiv Prepr. arXiv1906.08237, 2019."},{"key":"e_1_3_2_1_5_1","volume-title":"arXiv1904.08109","author":"Yang L.","year":"2019","unstructured":"L. Yang , Liu and Song , \" Contextual Aware Joint Probability Model Towards Question Answering System ,\" ar Xiv Prepr . arXiv1904.08109 , 2019 . L. Yang, Liu and Song, \"Contextual Aware Joint Probability Model Towards Question Answering System,\" arXiv Prepr. arXiv1904.08109, 2019."},{"key":"e_1_3_2_1_6_1","volume-title":"arXiv1805.03356","author":"Song C.-C. J.","year":"2018","unstructured":"C.-C. J. Song , Yuhang and Yang , Chao and Shen , Yeji and Wang , Peng and Huang , Qin and Kuo , \" Segmentation prediction and guidance network for image inpainting,\" ar Xiv Prepr . arXiv1805.03356 , 2018 . C.-C. J. Song, Yuhang and Yang, Chao and Shen, Yeji and Wang, Peng and Huang, Qin and Kuo, \"Segmentation prediction and guidance network for image inpainting,\" arXiv Prepr. arXiv1805.03356, 2018."},{"key":"e_1_3_2_1_7_1","volume-title":"BERT: Pre-training of deep bidirectional transformers,\" arXiv:1810.04805","author":"Devlin J.","year":"2017","unstructured":"J. Devlin , M. Chang , K. Lee , and K. Toutanova , \" BERT: Pre-training of deep bidirectional transformers,\" arXiv:1810.04805 , 2017 . J. Devlin, M. Chang, K. Lee, and K. Toutanova, \"BERT: Pre-training of deep bidirectional transformers,\" arXiv:1810.04805, 2017."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"M. Peters","year":"2018","unstructured":"M. Peters et al., \" Deep Contextualized Word Representations ,\" in Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , Volume 1 (Long Papers) , 2018 . M. Peters et al., \"Deep Contextualized Word Representations,\" in Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), 2018."},{"key":"e_1_3_2_1_9_1","volume-title":"Distributed Representations of Words and Phrases and their Compositionality arXiv: 1310. 4546v1 [ cs. CL ]","author":"Mikolov T.","year":"2013","unstructured":"T. Mikolov , K. Chen , G. Corrado , and J. Dean , \" Distributed Representations of Words and Phrases and their Compositionality arXiv: 1310. 4546v1 [ cs. CL ] 16 Oct 2013 ,\" arXiv Prepr . arXiv1310.4546, 2013. T. Mikolov, K. Chen, G. Corrado, and J. Dean, \"Distributed Representations of Words and Phrases and their Compositionality arXiv: 1310. 4546v1 [ cs. CL ] 16 Oct 2013,\" arXiv Prepr. arXiv1310.4546, 2013."},{"key":"e_1_3_2_1_10_1","first-page":"1532","volume-title":"Glove: Global Vectors for Word Representation,\" in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Pennington J.","year":"2014","unstructured":"J. Pennington , R. Socher , and C. Manning , \" Glove: Global Vectors for Word Representation,\" in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) , 2014 , pp. 1532 -- 1543 . J. Pennington, R. Socher, and C. Manning, \"Glove: Global Vectors for Word Representation,\" in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014, pp. 1532--1543."},{"key":"e_1_3_2_1_11_1","volume-title":"Intell. Stat.","author":"Bartunov D.","year":"2016","unstructured":"D. Bartunov , Sergey and Kondrashkin , Dmitry and Osokin , Anton and Vetrov , \"Breaking sticks and ambiguities with adaptive skip-gram,\" Artif . Intell. Stat. , 2016 . D. Bartunov, Sergey and Kondrashkin, Dmitry and Osokin, Anton and Vetrov, \"Breaking sticks and ambiguities with adaptive skip-gram,\" Artif. Intell. Stat., 2016."},{"key":"e_1_3_2_1_12_1","volume-title":"Pre-training of deep bidirectional transformers for language understanding,\" arXiv Prepr. arXiv1810.04805","author":"Devlin K.","year":"2018","unstructured":"K. Devlin , Jacob and Chang , Ming-Wei and Lee , Kenton and Toutanova , \"Bert : Pre-training of deep bidirectional transformers for language understanding,\" arXiv Prepr. arXiv1810.04805 , 2018 . K. Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, \"Bert: Pre-training of deep bidirectional transformers for language understanding,\" arXiv Prepr. arXiv1810.04805, 2018."},{"key":"e_1_3_2_1_13_1","unstructured":"I. Radford Alec and Wu Jeffrey and Child Rewon and Luan David and Amodei Dario and Sutskever \"Language models are unsupervised multitask learners \" OpenAI Blog 2019. I. Radford Alec and Wu Jeffrey and Child Rewon and Luan David and Amodei Dario and Sutskever \"Language models are unsupervised multitask learners \" OpenAI Blog 2019."},{"key":"e_1_3_2_1_14_1","volume-title":"A Robustly Optimized BERT Pretraining Approach,\" arXiv Prepr. arXiv1907.11692","author":"Liu V.","year":"2019","unstructured":"V. Liu , Yinhan and Ott , Myle and Goyal , Naman and Du , Jingfei and Joshi , Mandar and Chen , Danqi and Levy , Omer and Lewis , Mike and Zettlemoyer , Luke and Stoyanov , \"RoBERTa : A Robustly Optimized BERT Pretraining Approach,\" arXiv Prepr. arXiv1907.11692 , 2019 . V. Liu, Yinhan and Ott, Myle and Goyal, Naman and Du, Jingfei and Joshi, Mandar and Chen, Danqi and Levy, Omer and Lewis, Mike and Zettlemoyer, Luke and Stoyanov, \"RoBERTa: A Robustly Optimized BERT Pretraining Approach,\" arXiv Prepr. arXiv1907.11692, 2019."},{"key":"e_1_3_2_1_15_1","volume-title":"arXiv1907.10529","author":"Joshi O.","year":"2019","unstructured":"O. Joshi , Mandar and Chen , Danqi and Liu , Yinhan and Weld , Daniel S and Zettlemoyer , Luke and Levy , \"Span BERT Improving Pre-training by Representing and Predicting Spans ,\" ar Xiv Prepr . arXiv1907.10529 , 2019 . O. Joshi, Mandar and Chen, Danqi and Liu, Yinhan and Weld, Daniel S and Zettlemoyer, Luke and Levy, \"SpanBERT Improving Pre-training by Representing and Predicting Spans,\" arXiv Prepr. arXiv1907.10529, 2019."},{"key":"e_1_3_2_1_16_1","volume-title":"BiDAF,\" ICLR","author":"Seo M.","year":"2017","unstructured":"M. Seo , A. Kembhavi , A. Farhadi , and H. Hajishirzi , \" BiDAF,\" ICLR , 2017 . M. Seo, A. Kembhavi, A. Farhadi, and H. Hajishirzi, \"BiDAF,\" ICLR, 2017."},{"key":"e_1_3_2_1_17_1","volume-title":"arXiv1409.0473","author":"Bahdanau Y.","year":"2014","unstructured":"Y. Bahdanau , Dzmitry and Cho , Kyunghyun and Bengio , \" Neural machine translation by jointly learning to align and translate,\" ar Xiv Prepr . arXiv1409.0473 , 2014 . Y. Bahdanau, Dzmitry and Cho, Kyunghyun and Bengio, \"Neural machine translation by jointly learning to align and translate,\" arXiv Prepr. arXiv1409.0473, 2014."},{"key":"e_1_3_2_1_18_1","volume-title":"Attention-over-Attention Neural Networks for Reading Comprehension","author":"Cui Y.","year":"2017","unstructured":"Y. Cui , Z. Chen , S. Wei , S. Wang , T. Liu , and G. Hu , \" Attention-over-Attention Neural Networks for Reading Comprehension ,\" 2017 . Y. Cui, Z. Chen, S. Wei, S. Wang, T. Liu, and G. Hu, \"Attention-over-Attention Neural Networks for Reading Comprehension,\" 2017."},{"key":"e_1_3_2_1_19_1","volume-title":"Image captioning with semantic attention,\" in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition","author":"You Q.","year":"2016","unstructured":"Q. You , H. Jin , Z. Wang , C. Fang , and J. Luo , \" Image captioning with semantic attention,\" in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition , 2016 . Q. You, H. Jin, Z. Wang, C. Fang, and J. Luo, \"Image captioning with semantic attention,\" in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016."},{"key":"e_1_3_2_1_20_1","volume-title":"xiaoyan zhu, and L. Zhao, \"Attention-based LSTM for Aspect-level Sentiment Classification","author":"Wang Y.","year":"2016","unstructured":"Y. Wang , M. Huang , xiaoyan zhu, and L. Zhao, \"Attention-based LSTM for Aspect-level Sentiment Classification ,\" 2016 . Y. Wang, M. Huang, xiaoyan zhu, and L. Zhao, \"Attention-based LSTM for Aspect-level Sentiment Classification,\" 2016."},{"key":"e_1_3_2_1_21_1","volume-title":"Cicero Nogueira dos and Yu, Mo and Xiang, Bing and Zhou, Bowen and Bengio, \"A structured self-attentive sentence embedding,\" arXiv Prepr. arXiv1703.03130","author":"Lin Y.","year":"2017","unstructured":"Y. Lin , Zhouhan and Feng , Minwei and Santos , Cicero Nogueira dos and Yu, Mo and Xiang, Bing and Zhou, Bowen and Bengio, \"A structured self-attentive sentence embedding,\" arXiv Prepr. arXiv1703.03130 , 2017 . Y. Lin, Zhouhan and Feng, Minwei and Santos, Cicero Nogueira dos and Yu, Mo and Xiang, Bing and Zhou, Bowen and Bengio, \"A structured self-attentive sentence embedding,\" arXiv Prepr. arXiv1703.03130, 2017."},{"key":"e_1_3_2_1_22_1","volume-title":"The 31st Conference on Neural Information Processing Systems (NIPS 2017)","author":"A. Vaswani","year":"2017","unstructured":"A. Vaswani et al., \" Attention Is All You Need [Transformer],\" in The 31st Conference on Neural Information Processing Systems (NIPS 2017) , 2017 . A. Vaswani et al., \"Attention Is All You Need [Transformer],\" in The 31st Conference on Neural Information Processing Systems (NIPS 2017), 2017."},{"key":"e_1_3_2_1_23_1","first-page":"2440","author":"Sukhbaatar S.","year":"2015","unstructured":"S. Sukhbaatar , J. Weston , and R. Fergus , \"End-to-end memory networks,\" Adv. Neural Inf. Process. Syst. , pp. 2440 -- 2448 , 2015 . S. Sukhbaatar, J. Weston, and R. Fergus, \"End-to-end memory networks,\" Adv. Neural Inf. Process. Syst., pp. 2440--2448, 2015.","journal-title":"\"End-to-end memory networks,\" Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_2_1_24_1","unstructured":"M. Hu F. Wei Y. Peng Z. Huang N. Yang and D. Li \"Read + Verify: Machine Reading Comprehension with Unanswerable Questions \" no. 1. M. Hu F. Wei Y. Peng Z. Huang N. Yang and D. Li \"Read + Verify: Machine Reading Comprehension with Unanswerable Questions \" no. 1."},{"key":"e_1_3_2_1_25_1","volume-title":"QANET: COMBINING LOCAL CONVOLUTION WITH GLOBAL SELF-ATTENTION FOR READING COMPRE- HENSION,\" Ulster Med. J","author":"Brown D. C.","year":"1993","unstructured":"D. C. Brown and O. B. Eden , \" QANET: COMBINING LOCAL CONVOLUTION WITH GLOBAL SELF-ATTENTION FOR READING COMPRE- HENSION,\" Ulster Med. J ., 1993 . D. C. Brown and O. B. Eden, \"QANET: COMBINING LOCAL CONVOLUTION WITH GLOBAL SELF-ATTENTION FOR READING COMPRE- HENSION,\" Ulster Med. J., 1993."},{"key":"e_1_3_2_1_26_1","first-page":"1","volume-title":"Int. Conf. Learn. Represent.","author":"Shuohang","year":"2017","unstructured":"Shuohang {Wang} and Jing {Jiang}, \" Machine Comprehension Using Match- LSTM and Answer Pointer ,\" Int. Conf. Learn. Represent. , p. 1 , 2017 . Shuohang {Wang} and Jing {Jiang}, \"Machine Comprehension Using Match-LSTM and Answer Pointer,\" Int. Conf. Learn. Represent., p. 1, 2017."},{"key":"e_1_3_2_1_27_1","volume-title":"the Rest Can Be Pruned,\" arXiv Prepr. arXiv1905.09418","author":"Voita I.","year":"2019","unstructured":"I. Voita , Elena and Talbot , David and Moiseev , Fedor and Sennrich , Rico and Titov , \" Analyzing Multi-Head Self-Attention Specialized Heads Do the Heavy Lifting , the Rest Can Be Pruned,\" arXiv Prepr. arXiv1905.09418 , 2019 . I. Voita, Elena and Talbot, David and Moiseev, Fedor and Sennrich, Rico and Titov, \"Analyzing Multi-Head Self-Attention Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned,\" arXiv Prepr. arXiv1905.09418, 2019."},{"key":"e_1_3_2_1_28_1","volume-title":"Luu Anh and Hui, \"Multi-cast attention networks for retrieval-based question answering and response prediction,\" arXiv Prepr. arXiv1806.00778","author":"Tay S. C.","year":"2018","unstructured":"S. C. Tay , Yi and Tuan , Luu Anh and Hui, \"Multi-cast attention networks for retrieval-based question answering and response prediction,\" arXiv Prepr. arXiv1806.00778 , 2018 . S. C. Tay, Yi and Tuan, Luu Anh and Hui, \"Multi-cast attention networks for retrieval-based question answering and response prediction,\" arXiv Prepr. arXiv1806.00778, 2018."},{"key":"e_1_3_2_1_29_1","volume-title":"Multi-Head Attention with Disagreement Regularization","author":"Li J.","year":"2019","unstructured":"J. Li , Z. Tu , B. Yang , M. R. Lyu , and T. Zhang , \" Multi-Head Attention with Disagreement Regularization ,\" 2019 . J. Li, Z. Tu, B. Yang, M. R. Lyu, and T. Zhang, \"Multi-Head Attention with Disagreement Regularization,\" 2019."}],"event":{"name":"ICAIP 2019: 2019 3rd International Conference on Advances in Image Processing","sponsor":["Southwest Jiaotong University"],"location":"Chengdu China","acronym":"ICAIP 2019"},"container-title":["Proceedings of the 2019 3rd International Conference on Advances in Image Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3373419.3373430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,7]],"date-time":"2023-03-07T18:32:16Z","timestamp":1678213936000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3373419.3373430"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,8]]},"references-count":29,"alternative-id":["10.1145\/3373419.3373430","10.1145\/3373419"],"URL":"https:\/\/doi.org\/10.1145\/3373419.3373430","relation":{},"subject":[],"published":{"date-parts":[[2019,11,8]]},"assertion":[{"value":"2020-01-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}