{"type":"ScholarlyArticle","title":"CNN-Based Chinese NER with Lexicon Rethinking","authors":[{"name":"Tao Gui","slug":"tao-gui","given":"Tao","family":"Gui","affiliation":"School of Computer Science , Fudan University , Shanghai , China"},{"name":"Ruotian Ma","slug":"ruotian-ma","given":"Ruotian","family":"Ma","affiliation":"School of Computer Science , Fudan University , Shanghai , China"},{"name":"Qi Zhang","slug":"qi-zhang","given":"Qi","family":"Zhang","affiliation":"School of Computer Science , Fudan University , Shanghai , China"},{"name":"Lujun Zhao","slug":"lujun-zhao","given":"Lujun","family":"Zhao","affiliation":"School of Computer Science , Fudan University , Shanghai , China"},{"name":"Yu-Gang Jiang","slug":"yu-gang-jiang","given":"Yu-Gang","family":"Jiang","affiliation":"School of Computer Science , Fudan University , Shanghai , China; Jilian Technology Group (Video++) , Shanghai , China; Guangzhou Major Guangzhou City"},{"name":"Xuanjing Huang","slug":"xuanjing-huang","given":"Xuanjing","family":"Huang","affiliation":"School of Computer Science , Fudan University , Shanghai , China; 市⻓长 ⻓长隆隆 公园"}],"abstract":"Character-level Chinese named entity recognition (NER) that applies long short-term memory (LSTM) to incorporate lexicons has achieved great success. However, this method fails to fully exploit GPU parallelism and candidate lexicons can conflict. In this work, we propose a faster alternative to Chinese NER: a convolutional neural network (CNN)-based method that incorporates lexicons using a rethinking mechanism. The proposed method can model all the characters and potential words that match the sentence in parallel. In addition, the rethinking mechanism can address the word conflict by feeding back the high-level features to refine the networks. Experimental results on four datasets show that the proposed method can achieve better performance than both word-level and character-level baseline methods. In addition, the proposed method performs up to 3.21 times faster than state-of-the-art methods, while realizing better performance.","doi":"10.24963/ijcai.2019/692","url":"https://ijcai.org/proceedings/2019/692","pdf":"https://ijcai.org/proceedings/2019/0692.pdf","markdown":"https://ijcai.org/proceedings/2019/692.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/692","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Natural Language Processing","track":"Main track","number":692,"pages":{"first":4982,"last":4988},"keywords":["Natural Language Processing: Named Entities","Natural Language Processing: Tagging, chunking, and parsing","Natural Language Processing: Phonology, Morphology, and word segmentation"],"videos":[],"references":[{"position":1,"raw":"[Bunescu and Mooney, 2005] Razvan C Bunescu and Ray- mond J Mooney. A shortest path dependency kernel for relation extraction. In HLT-EMNLP, 2005.","title":"A shortest path dependency kernel for relation extraction","authors":"C Razvan, Raymond J Bunescu, Mooney","year":"2005","venue":"HLT-EMNLP","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Che et al., 2013] Wanxiang Che, Mengqiu Wang, Christo- pher D Manning, and Ting Liu. Named entity recognition with bilingual constraints. In NAACL, pages 52-62, 2013.","title":"Named entity recognition with bilingual constraints","authors":"Wanxiang Che, Mengqiu Wang, Christopher D Manning, Ting Liu","year":"2013","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2006] Aitao Chen, Fuchun Peng, Roy Shan, and Gordon Sun. Chinese named entity recognition with conditional probabilistic models. In SIGHAN Workshop on Chinese Language Processing, 2006.","title":"Chinese named entity recognition with conditional probabilistic models","authors":"Chen","year":"2006","venue":"SIGHAN Workshop on Chinese Language Processing","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2015] Yubo Chen, Liheng Xu, Kang Liu, Daojian Zeng, and Jun Zhao. Event extraction via dynamic multi-pooling convolutional neural networks. In ACL-IJCNLP, volume 1, pages 167-176, 2015.","title":"Event extraction via dynamic multi-pooling convolutional neural networks","authors":"Yubo Chen, Liheng Xu, Kang Liu, Daojian Zeng, Jun Zhao","year":"2015","venue":"ACL-IJCNLP","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen et al., 2018] Qian Chen, Zhen-Hua Ling, and Xiaodan Zhu. Enhancing sentence embedding with generalized pooling. In COLING, pages 1815-1826, 2018.","title":"Enhancing sentence embedding with generalized pooling","authors":"Qian Chen, Zhen-Hua Ling, Xiaodan Zhu","year":"2018","venue":"COLING","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Diefenbach et al., 2018] Dennis Diefenbach, Vanessa Lopez, Kamal Singh, and Pierre Maret. Core techniques of question answering systems over knowledge bases: a survey. KAIS, 55(3):529-569, 2018.","title":"Core techniques of question answering systems over knowledge bases: a survey","authors":"Dennis Diefenbach, Vanessa Lopez, Kamal Singh, Pierre Maret","year":"2018","venue":"KAIS","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Dong et al., 2016] Chuanhai Dong, Jiajun Zhang, Chengqing Zong, Masanori Hattori, and Hui Di. Character-based lstm-crf with radical-level features for chinese named entity recognition. In Natural Language Understanding and Intelligent Applications, pages 239-250. Springer, 2016.","title":"Character-based lstm-crf with radical-level features for chinese named entity recognition","authors":"Dong","year":"2016","venue":"Natural Language Understanding and Intelligent Applications","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Duan and Zheng, 2011] Huanzhong Duan and Yan Zheng. A study on features of the crfs-based chinese named entity recognition. IJAI, 3(2):287-294, 2011.","title":"A study on features of the crfs-based chinese named entity recognition","authors":"Zheng Duan, Huanzhong Duan, Yan Zheng","year":"2011","venue":"IJAI","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[He and Sun, 2016] Hangfeng He and Xu Sun. F-score driven max margin neural network for named entity recognition in chinese social media. arXiv preprint arXiv:1611.04234, 2016.","title":"Hangfeng He and Xu Sun. F-score driven max margin neural network for named entity recognition in chinese social media","authors":"Sun He","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[He and Sun, 2017] Hangfeng He and Xu Sun. A unified model for cross-domain and semi-supervised named entity recognition in chinese social media. In AAAI, 2017.","title":"Hangfeng He and Xu Sun. A unified model for cross-domain and semi-supervised named entity recognition in chinese social media","authors":"Sun He","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Hochreiter and Schmidhuber, 1997] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural computation, 9(8):1735-1780, 1997.","title":"Long short-term memory","authors":"Schmidhuber Hochreiter, Sepp Hochreiter, Jürgen Schmidhuber","year":"1997","venue":"Neural computation","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kim, 2014] Yoon Kim. Convolutional neural networks for sentence classification. EMNLP, pages 1746-1751, 2014.","title":"Convolutional neural networks for sentence classification","authors":"Yoon Kim","year":"2014","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kingma and Ba, 2014] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Levow, 2006] Gina-Anne Levow. The third international chinese language processing bakeoff: Word segmentation and named entity recognition. In SIGHAN Workshop on Chinese Language Processing, pages 108-117, 2006.","title":"The third international chinese language processing bakeoff: Word segmentation and named entity recognition","authors":"Gina-Anne Levow","year":"2006","venue":"SIGHAN Workshop on Chinese Language Processing","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Li et al., 2018] Xin Li, Zequn Jie, Jiashi Feng, Changsong Liu, and Shuicheng Yan. Learning with rethinking: Recurrently improving convolutional neural networks through feedback. Pattern Recognition, 2018.","title":"Learning with rethinking: Recurrently improving convolutional neural networks through feedback","authors":"Xin Li, Zequn Jie, Jiashi Feng, Changsong Liu, Shuicheng Yan","year":"2018","venue":"Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lu et al., 2016] Yanan Lu, Yue Zhang, and Dong-Hong Ji. Multi-prototype chinese character embedding. In LREC, 2016.","title":"Multi-prototype chinese character embedding","authors":"Lu","year":"2016","venue":"LREC","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ma and Hovy, 2016] Xuezhe Ma and Eduard Hovy. End-to- end sequence labeling via bi-directional lstm-cnns-crf. In ACL, volume 1, pages 1064-1074, 2016.","title":"Xuezhe Ma and Eduard Hovy. End-toend sequence labeling via bi-directional lstm-cnns-crf","authors":"Hovy Ma","year":"2016","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ma et al., 2014] Guojie Ma, Xingshan Li, and Keith Rayner. Word segmentation of overlapping ambiguous strings during chinese reading. Journal of Experimen- tal Psychology: Human Perception and Performance, 40(3):1046, 2014.","title":"Word segmentation of overlapping ambiguous strings during chinese reading","authors":"Ma","year":"2014","venue":"Journal of Experimental Psychology: Human Perception and Performance","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Mikolov et al., 2013] Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. Distributed repre- sentations of words and phrases and their compositionality. In NeurIPS, pages 3111-3119, 2013.","title":"Distributed representations of words and phrases and their compositionality","authors":"Mikolov","year":"2013","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Passos et al., 2014] Alexandre Passos, Vineet Kumar, and Andrew McCallum. Lexicon infused phrase embeddings for named entity resolution. CoNLL-2014, page 78, 2014.","title":"Lexicon infused phrase embeddings for named entity resolution","authors":"Alexandre Passos, Vineet Kumar, Andrew Mccallum","year":"2014","venue":"CoNLL-2014","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Peng and Dredze, 2015] Nanyun Peng and Mark Dredze. Named entity recognition for chinese social media with jointly trained embeddings. In EMNLP, 2015.","title":"Named entity recognition for chinese social media with jointly trained embeddings","authors":"Dredze Peng, Nanyun Peng, Mark Dredze","year":"2015","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Peng and Dredze, 2016] Nanyun Peng and Mark Dredze. Improving named entity recognition for chinese social media with word segmentation representation learning. In ACL, page 149, 2016.","title":"Improving named entity recognition for chinese social media with word segmentation representation learning","authors":"Dredze Peng, Nanyun Peng, Mark Dredze","year":"2016","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Strubell et al., 2017] Emma Strubell, Patrick Verga, David Belanger, and Andrew McCallum. Fast and accurate entity recognition with iterated dilated convolutions. In EMNLP, pages 2670-2680, 2017.","title":"Fast and accurate entity recognition with iterated dilated convolutions","authors":"Emma Strubell, Patrick Verga, David Belanger, Andrew Mccallum","year":"2017","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wang et al., 2013] Mengqiu Wang, Wanxiang Che, and Christopher D Manning. Effective bilingual constraints for semi-supervised learning of named entity recognizers. In AAAI, 2013.","title":"Effective bilingual constraints for semi-supervised learning of named entity recognizers","authors":"Wang","year":"2013","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wang et al., 2018] Shiyao Wang, Minlie Huang, and Zhi- dong Deng. Densely connected cnn with multi-scale feature attention for text classification. In IJCAI, 2018.","title":"Densely connected cnn with multi-scale feature attention for text classification","authors":"Wang","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/621"},{"position":26,"raw":"[Weischedel et al., 2011] Ralph Weischedel, Sameer Prad- han, Lance Ramshaw, Martha Palmer, Nianwen Xue, Mitchell Marcus, Ann Taylor, Craig Greenberg, Eduard Hovy, Robert Belvin, et al. Ontonotes release 4.0. LDC2011T03, Philadelphia, Penn.: Linguistic Data Consortium, 2011.","title":"Ontonotes release 4.0. LDC2011T03","authors":"Ralph Weischedel, Sameer Pradhan, Lance Ramshaw, Martha Palmer, Nianwen Xue, Mitchell Marcus, Ann Taylor, Craig Greenberg, Eduard Hovy, Robert Belvin","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Yang et al., 2016] Jie Yang, Zhiyang Teng, Meishan Zhang, and Yue Zhang. Combining discrete and neural features for sequence labeling. In CICLing. Springer, 2016.","title":"Combining discrete and neural features for sequence labeling","authors":"Jie Yang, Zhiyang Teng, Meishan Zhang, Yue Zhang","year":"2016","venue":"CICLing","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhang and Yang, 2018] Yue Zhang and Jie Yang. Chinese ner using lattice lstm. ACL, 1:1554-1564, 2018.","title":"Chinese ner using lattice lstm","authors":"Yue Zhang, Jie Yang","year":"2018","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhang et al., 2006] Suxiang Zhang, Ying Qin, Juan Wen, and Xiaojie Wang. Word segmentation and named entity recognition for sighan bakeoff3. In SIGHAN Workshop on Chinese Language Processing, pages 158-161, 2006.","title":"Word segmentation and named entity recognition for sighan bakeoff3","authors":"Suxiang Zhang, Ying Qin, Juan Wen, Xiaojie Wang","year":"2006","venue":"SIGHAN Workshop on Chinese Language Processing","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhou et al., 2013] Junsheng Zhou, Weiguang Qu, and Fen Zhang. Chinese named entity recognition via joint identification and categorization. Chinese journal of electronics, 22(2):225-230, 2013.","title":"Chinese named entity recognition via joint identification and categorization","authors":"Junsheng Zhou, Weiguang Qu, Fen Zhang","year":"2013","venue":"Chinese journal of electronics","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}