{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T19:51:07Z","timestamp":1771703467801,"version":"3.50.1"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"7","license":[{"start":{"date-parts":[[2023,7,20]],"date-time":"2023-07-20T00:00:00Z","timestamp":1689811200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2023,7,31]]},"abstract":"<jats:p>Named entity recognition (NER) is a fundamental task for information extraction applications. NER is challenging because of semantic ambiguities in academic literature, especially for non-Latin languages. Besides word semantic information, recognizing Chinese named entities needs to consider word boundary information, as words contained in Chinese texts are not separated with spaces. Leveraging word boundary information could help to determine entity boundaries and thus improve entity recognition performance. In this article, we propose to combine word boundary information and semantic information for named entity recognition based on multi-task adversarial learning. Specifically, we learn commonly shared boundary information of entities from multiple kinds of tasks, including Chinese word segmentation (CWS), part-of-speech (POS) tagging, and entity recognition, with adversarial learning. We learn task-specific semantic information of words from these tasks and combine the learned boundary information with the semantic information to improve entity recognition with multi-task learning. We then propose a compression method based on improved clustering to accelerate the proposed model. We conduct extensive experiments on four public benchmark datasets and two private datasets, compared with state-of-the-art baseline models, and the experimental results demonstrate that our model achieves considerable performance improvements on various evaluation datasets.<\/jats:p>","DOI":"10.1145\/3603626","type":"journal-article","created":{"date-parts":[[2023,6,6]],"date-time":"2023-06-06T19:03:38Z","timestamp":1686078218000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Adversarial Multi-task Learning for Efficient Chinese Named Entity Recognition"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2793-0579","authenticated-orcid":false,"given":"Yibo","family":"Yan","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9558-3787","authenticated-orcid":false,"given":"Peng","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Data Science and Engineering, East China Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5877-7387","authenticated-orcid":false,"given":"Dawei","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7293-4975","authenticated-orcid":false,"given":"Fangzhou","family":"Yang","sequence":"additional","affiliation":[{"name":"Group of Artificial Intelligence and Big Data, Seek Data Inc., China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4863-3432","authenticated-orcid":false,"given":"Yifeng","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Data Science and Engineering, East China Normal University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,7,20]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"e_1_3_1_3_2","first-page":"724","volume-title":"HLT-EMNLP","author":"Bunescu Razvan C.","year":"2005","unstructured":"Razvan C. Bunescu and Raymond J. Mooney. 2005. A shortest path dependency kernel for relation extraction. In HLT-EMNLP. 724\u2013731."},{"key":"e_1_3_1_4_2","first-page":"182","volume-title":"EMNLP","author":"Cao Pengfei","year":"2018","unstructured":"Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao, and Shengping Liu. 2018. Adversarial transfer learning for Chinese named entity recognition with self-attention mechanism. In EMNLP. 182\u2013192."},{"key":"e_1_3_1_5_2","first-page":"52","volume-title":"NAACL","author":"Che Wanxiang","year":"2013","unstructured":"Wanxiang Che, Mengqiu Wang, Christopher D. Manning, and Ting Liu. 2013. Named entity recognition with bilingual constraints. In NAACL. 52\u201362."},{"key":"e_1_3_1_6_2","first-page":"173","volume-title":"SIGHAN","author":"Chen Aitao","year":"2006","unstructured":"Aitao Chen, Fuchun Peng, Roy Shan, and Gordon Sun. 2006. Chinese named entity recognition with conditional probabilistic models. In SIGHAN. 173\u2013176."},{"key":"e_1_3_1_7_2","article-title":"Delinquent events prediction in temporal networked-guarantee loans","author":"Cheng Dawei","year":"2020","unstructured":"Dawei Cheng, Zhibin Niu, and Liqing Zhang. 2020. Delinquent events prediction in temporal networked-guarantee loans. IEEE Trans. Neural Netw. Learn. Syst. 34, 4 (2020).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00104"},{"key":"e_1_3_1_9_2","first-page":"1462","volume-title":"ACL","author":"Ding Ruixue","year":"2019","unstructured":"Ruixue Ding, Pengjun Xie, Xiaoyan Zhang, Wei Lu, Linlin Li, and Luo Si. 2019. A neural multi-digraph model for Chinese NER with gazetteers. In ACL. 1462\u20131467."},{"key":"e_1_3_1_10_2","first-page":"239","volume-title":"NLPCC","author":"Dong Chuanhai","year":"2016","unstructured":"Chuanhai Dong, Jiajun Zhang, Chengqing Zong, Masanori Hattori, and Hui Di. 2016. Character-based LSTM-CRF with radical-level features for Chinese named entity recognition. In NLPCC. 239\u2013250."},{"key":"e_1_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Thomas Elsken Jan Hendrik Metzen and Frank Hutter. 2019. Neural architecture search: A survey. J. Mach. Learn. Res. 20 1 (2019) 1997\u20132017.","DOI":"10.1007\/978-3-030-05318-5_11"},{"key":"e_1_3_1_12_2","first-page":"1608","volume-title":"ACL","author":"Fader Anthony","year":"2013","unstructured":"Anthony Fader, Luke Zettlemoyer, and Oren Etzioni. 2013. Paraphrase-driven learning for open question answering. In ACL. 1608\u20131618."},{"key":"e_1_3_1_13_2","first-page":"2413","volume-title":"CIKM","author":"Fan Mengzhen","year":"2020","unstructured":"Mengzhen Fan, Dawei Cheng, Fangzhou Yang, Siqiang Luo, Yifeng Luo, Weining Qian, and Aoying Zhou. 2020. Fusing global domain information and local semantic information to classify financial documents. In CIKM. 2413\u20132420."},{"key":"e_1_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Jianping Gou Baosheng Yu Stephen J. Maybank and Dacheng Tao. 2021. Knowledge distillation: A survey. Int. J. Comput. Vis. 129 6 (2021) 1789\u20131819.","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_1_15_2","first-page":"4982","volume-title":"IJCAI","author":"Gui Tao","year":"2019","unstructured":"Tao Gui, Ruotian Ma, Qi Zhang, Lujun Zhao, Yu-Gang Jiang, and Xuanjing Huang. 2019. CNN-based Chinese NER with lexicon rethinking. In IJCAI. 4982\u20134988."},{"key":"e_1_3_1_16_2","first-page":"1039","volume-title":"EMNLP-IJCNLP","author":"Gui Tao","year":"2019","unstructured":"Tao Gui, Yicheng Zou, Qi Zhang, Minlong Peng, Jinlan Fu, Zhongyu Wei, and Xuanjing Huang. 2019. A lexicon-based graph neural network for Chinese NER. In EMNLP-IJCNLP. 1039\u20131049."},{"key":"e_1_3_1_17_2","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"Han Song","year":"2015","unstructured":"Song Han, Huizi Mao, and William J. Dally. 2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. arXiv preprint arXiv:1510.00149 (2015).","journal-title":"arXiv preprint arXiv:1510.00149"},{"key":"e_1_3_1_18_2","first-page":"713","volume-title":"EACL","author":"He Hangfeng","year":"2017","unstructured":"Hangfeng He and Xu Sun. 2017. F-score driven max margin neural network for named entity recognition in Chinese social media. In EACL. 713\u2013718."},{"key":"e_1_3_1_19_2","first-page":"3216","volume-title":"AAAI","author":"He Hangfeng","year":"2017","unstructured":"Hangfeng He and Xu Sun. 2017. A unified model for cross-domain and semi-supervised named entity recognition in Chinese social media. In AAAI. 3216\u20133222."},{"key":"e_1_3_1_20_2","article-title":"Bidirectional LSTM-CRF models for sequence tagging","author":"Huang Zhiheng","year":"2015","unstructured":"Zhiheng Huang, Wei Xu, and Kai Yu. 2015. Bidirectional LSTM-CRF models for sequence tagging. arXiv preprint arXiv:1508.01991 (2015).","journal-title":"arXiv preprint arXiv:1508.01991"},{"key":"e_1_3_1_21_2","first-page":"4119","volume-title":"NIPS","author":"Ji Yu","year":"2018","unstructured":"Yu Ji, Ling Liang, Lei Deng, Youyang Zhang, Youhui Zhang, and Yuan Xie. 2018. TETRIS: Tile-matching the tremendous irregular sparsity. In NIPS. 4119\u20134129."},{"key":"e_1_3_1_22_2","first-page":"108","volume-title":"SIGHAN","author":"Levow Gina-Anne","year":"2006","unstructured":"Gina-Anne Levow. 2006. The Third International Chinese Language Processing Bakeoff: Word segmentation and named entity recognition. In SIGHAN. 108\u2013117."},{"key":"e_1_3_1_23_2","first-page":"6836","volume-title":"ACL","author":"Li Xiaonan","year":"2020","unstructured":"Xiaonan Li, Hang Yan, Xipeng Qiu, and Xuanjing Huang. 2020. FLAT: Chinese NER using flat-lattice transformer. In ACL. 6836\u20136842."},{"key":"e_1_3_1_24_2","first-page":"4490","volume-title":"IJCAI","author":"Liang Xin","year":"2020","unstructured":"Xin Liang, Dawei Cheng, Fangzhou Yang, Yifeng Luo, Weining Qian, and Aoying Zhou. 2020. F-HMTC: Detecting financial events for investment decisions based on neural hierarchical multi-label text classification. In IJCAI. 4490\u20134496."},{"key":"e_1_3_1_25_2","first-page":"2379","volume-title":"NAACL","author":"Liu Wei","year":"2019","unstructured":"Wei Liu, Tongge Xu, Qinghua Xu, Jiayu Song, and Yueran Zu. 2019. An encoding strategy based word-character LSTM for Chinese NER. In NAACL. 2379\u20132389."},{"key":"e_1_3_1_26_2","first-page":"855","volume-title":"LREC","author":"Lu Yanan","year":"2016","unstructured":"Yanan Lu, Yue Zhang, and Donghong Ji. 2016. Multi-prototype chinese character embedding. In LREC. 855\u2013859."},{"key":"e_1_3_1_27_2","article-title":"Porous lattice-based transformer encoder for Chinese NER","author":"Mengge Xue","year":"2019","unstructured":"Xue Mengge, Yu Bowen, Liu Tingwen, Wang Bin, Meng Erli, and Li Quangang. 2019. Porous lattice-based transformer encoder for Chinese NER. arXiv preprint arXiv:1911.02733 (2019).","journal-title":"arXiv preprint arXiv:1911.02733"},{"key":"e_1_3_1_28_2","unstructured":"Andriy Mnih and Russ R. Salakhutdinov. 2007. Probabilistic matrix factorization. In NIPS . 1257\u20131264."},{"key":"e_1_3_1_29_2","first-page":"5951","volume-title":"ACL","author":"Peng Minlong","year":"2020","unstructured":"Minlong Peng, Ruotian Ma, Qi Zhang, and Xuanjing Huang. 2020. Simplify the usage of lexicon in Chinese NER. In ACL. 5951\u20135960."},{"key":"e_1_3_1_30_2","first-page":"548","volume-title":"EMNLP","author":"Peng Nanyun","year":"2015","unstructured":"Nanyun Peng and Mark Dredze. 2015. Named entity recognition for Chinese social media with jointly trained embeddings. In EMNLP. 548\u2013554."},{"key":"e_1_3_1_31_2","first-page":"149","volume-title":"ACL","author":"Peng Nanyun","year":"2016","unstructured":"Nanyun Peng and Mark Dredze. 2016. Improving named entity recognition for Chinese social media with word segmentation representation learning. In ACL. 149\u2013155."},{"key":"e_1_3_1_32_2","first-page":"1","volume-title":"DASFAA","author":"Cheng Fangzhou Yang Yifeng Luo Weining Qian andAoying Zhou Peng Zhu, Dawei","year":"2021","unstructured":"Fangzhou Yang Yifeng Luo Weining Qian andAoying Zhou Peng Zhu, Dawei Cheng. 2021. ZH-NER: Chinese named entity recognition with adversarial multi-task learning and self-attentions. In DASFAA. 1\u20138."},{"key":"e_1_3_1_33_2","first-page":"3821","volume-title":"EMNLP-IJCNLP","author":"Sui Dianbo","year":"2019","unstructured":"Dianbo Sui, Yubo Chen, Kang Liu, Jun Zhao, and Shengping Liu. 2019. Leverage lexical knowledge for Chinese named entity recognition via collaborative graph network. In EMNLP-IJCNLP. 3821\u20133831."},{"key":"e_1_3_1_34_2","first-page":"7039","volume-title":"AAAI","author":"Sun Changzhi","year":"2019","unstructured":"Changzhi Sun and Yuanbin Wu. 2019. Distantly supervised entity relation extraction with adapted manual annotations. In AAAI. 7039\u20137046."},{"key":"e_1_3_1_35_2","article-title":"Soft weight-sharing for neural network compression","author":"Ullrich Karen","year":"2017","unstructured":"Karen Ullrich, Edward Meeds, and Max Welling. 2017. Soft weight-sharing for neural network compression. arXiv preprint arXiv:1702.04008 (2017).","journal-title":"arXiv preprint arXiv:1702.04008"},{"key":"e_1_3_1_36_2","first-page":"52","volume-title":"AAAI","author":"Wang Mengqiu","year":"2013","unstructured":"Mengqiu Wang, Wanxiang Che, and Christopher D. Manning. 2013. Effective bilingual constraints for semi-supervised learning of named entity recognizers. In AAAI. 52\u201362."},{"key":"e_1_3_1_37_2","article-title":"OntoNotes 4.0","author":"Weischedel Ralph","year":"2011","unstructured":"Ralph Weischedel, Martha Palmer, Mitchell Marcus, Eduard Hovy, Sameer Pradhan, Lance Ramshaw, Nianwen Xue, Ann Taylor, Jeff Kaufman, Michelle Franchini et\u00a0al. 2011. OntoNotes 4.0. Linguistic Data Consortium LDC2011T03 (2011).","journal-title":"Linguistic Data Consortium LDC2011T03"},{"key":"e_1_3_1_38_2","first-page":"3342","volume-title":"WWW","author":"Wu Fangzhao","year":"2019","unstructured":"Fangzhao Wu, Junxin Liu, Chuhan Wu, Yongfeng Huang, and Xing Xie. 2019. Neural Chinese named entity recognition via CNN-LSTM-CRF and joint training with word segmentation. In WWW. 3342\u20133348."},{"key":"e_1_3_1_39_2","first-page":"5997","volume-title":"AAAI","author":"Xin Ji","year":"2018","unstructured":"Ji Xin, Yankai Lin, Zhiyuan Liu, and Maosong Sun. 2018. Improving neural fine-grained entity typing with knowledge attention. In AAAI. 5997\u20136004."},{"key":"e_1_3_1_40_2","article-title":"TENER: Adapting transformer encoder for name entity recognition","author":"Yan Hang","year":"2019","unstructured":"Hang Yan, Bocao Deng, Xiaonan Li, and Xipeng Qiu. 2019. TENER: Adapting transformer encoder for name entity recognition. arXiv preprint arXiv:1911.04474 (2019).","journal-title":"arXiv preprint arXiv:1911.04474"},{"key":"e_1_3_1_41_2","first-page":"184","volume-title":"NLPCC","author":"Yang Fan","year":"2018","unstructured":"Fan Yang, Jianhu Zhang, Gongshen Liu, Jie Zhou, Cheng Zhou, and Huanrong Sun. 2018. Five-stroke based CNN-BiRNN-CRF network for Chinese named entity recognition. In NLPCC. 184\u2013195."},{"key":"e_1_3_1_42_2","first-page":"140","volume-title":"CICLing","author":"Yang Jie","year":"2016","unstructured":"Jie Yang, Zhiyang Teng, Meishan Zhang, and Yue Zhang. 2016. Combining discrete and neural features for sequence labeling. In CICLing. 140\u2013154."},{"key":"e_1_3_1_43_2","first-page":"235","volume-title":"ACL","author":"Ye Zhixiu","year":"2018","unstructured":"Zhixiu Ye and Zhen-Hua Ling. 2018. Hybrid semi-Markov CRF for neural sequence labeling. In ACL. 235\u2013240."},{"key":"e_1_3_1_44_2","first-page":"158","volume-title":"SIGHAN","author":"Zhang Suxiang","year":"2006","unstructured":"Suxiang Zhang, Ying Qin, Juan Wen, and Xiaojie Wang. 2006. Word segmentation and named entity recognition for SIGHAN Bakeoff3. In SIGHAN. 158\u2013161."},{"key":"e_1_3_1_45_2","first-page":"1554","volume-title":"ACL","author":"Zhang Yue","year":"2018","unstructured":"Yue Zhang and Jie Yang. 2018. Chinese NER using lattice LSTM. In ACL. 1554\u20131564."},{"issue":"2","key":"e_1_3_1_46_2","first-page":"225","article-title":"Chinese named entity recognition via joint identification and categorization","volume":"22","author":"Zhou Junsheng","year":"2013","unstructured":"Junsheng Zhou, Weiguang Qu, and Fen Zhang. 2013. Chinese named entity recognition via joint identification and categorization. Chinese J. Electron. 22, 2 (2013), 225\u2013230.","journal-title":"Chinese J. Electron."},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3153261"},{"key":"e_1_3_1_48_2","first-page":"3384","volume-title":"NAACL","author":"Zhu Yuying","year":"2019","unstructured":"Yuying Zhu, Guoxin Wang, and B\u00f6rje F. Karlsson. 2019. CAN-NER: Convolutional attention network for Chinese named entity recognition. In NAACL. 3384\u20133393."}],"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\/3603626","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3603626","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:21Z","timestamp":1750178241000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603626"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,20]]},"references-count":47,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2023,7,31]]}},"alternative-id":["10.1145\/3603626"],"URL":"https:\/\/doi.org\/10.1145\/3603626","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"value":"2375-4699","type":"print"},{"value":"2375-4702","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,20]]},"assertion":[{"value":"2021-04-26","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-06-02","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-07-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}