{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T08:30:18Z","timestamp":1781598618172,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,2,11]],"date-time":"2022-02-11T00:00:00Z","timestamp":1644537600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Natural Science Foundation of China","award":["61572250"],"award-info":[{"award-number":["61572250"]}]},{"name":"Jiangsu Province Science & Technology Research Grant","award":["BE2017155"],"award-info":[{"award-number":["BE2017155"]}]},{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization, Jiangsu, China"},{"name":"National Key R&D Program of China","award":["2019YFC1711000"],"award-info":[{"award-number":["2019YFC1711000"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1811461"],"award-info":[{"award-number":["U1811461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,2,11]]},"DOI":"10.1145\/3488560.3498450","type":"proceedings-article","created":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T21:42:57Z","timestamp":1644961377000},"page":"726-734","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Pretraining Multi-modal Representations for Chinese NER Task with Cross-Modality Attention"],"prefix":"10.1145","author":[{"given":"Chengcheng","family":"Mai","sequence":"first","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengchuan","family":"Qiu","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiwen","family":"Luo","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyan","family":"Peng","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunfeng","family":"Yuan","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihua","family":"Huang","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,2,15]]},"reference":[{"key":"e_1_3_2_2_1_1","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."},{"key":"e_1_3_2_2_2_1","volume-title":"UNITER: UNiversal Image-TExt Representation Learning. In ECCV.","author":"Chen Yen-Chun","year":"2020","unstructured":"Yen-Chun Chen, Linjie Li, Licheng Yu, A. E. Kholy, Faisal Ahmed, Zhe Gan, Y. Cheng, and Jingjing Liu. 2020. UNITER: UNiversal Image-TExt Representation Learning. In ECCV."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Jaemin Cho Jiasen Lu Dustin Schwenk Hannaneh Hajishirzi and Aniruddha Kembhavi. 2020. X-LXMERT: Paint Caption and Answer Questions with Multi- Modal Transformers. In EMNLP.","DOI":"10.18653\/v1\/2020.emnlp-main.707"},{"key":"e_1_3_2_2_4_1","volume-title":"Courville","author":"de Vries Harm","year":"2017","unstructured":"Harm de Vries, Florian Strub, J\u00e9r\u00e9mie Mary, H. Larochelle, O. Pietquin, and Aaron C. Courville. 2017. Modulating early visual processing by language. In NIPS."},{"key":"e_1_3_2_2_5_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL.","author":"Devlin J.","year":"2019","unstructured":"J. Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331257"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1141"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"crossref","unstructured":"A. Graves and J. Schmidhuber. 2005. Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural networks : the official journal of the International Neural Network Society 18 5--6 (2005) 602--10.","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"crossref","unstructured":"Tao Gui Ruotian Ma Qi Zhang Lujun Zhao Yugang Jiang and Xuanjing Huang. 2019. CNN-Based Chinese NER with Lexicon Rethinking. In IJCAI.","DOI":"10.24963\/ijcai.2019\/692"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441738"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_2_12_1","unstructured":"Wonjae Kim Bokyung Son and Ildoo Kim. 2021. ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision. In ICML."},{"key":"e_1_3_2_2_13_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR."},{"key":"e_1_3_2_2_14_1","unstructured":"J. Lafferty A. McCallum and Fernando Pereira. 2001. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. In ICML."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"crossref","unstructured":"Gen Li Nan Duan Yuejian Fang Daxin Jiang and M. Zhou. 2020. Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training. In AAAI.","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"e_1_3_2_2_16_1","unstructured":"Xiaoya Li Jingrong Feng Yuxian Meng Qinghong Han Fei Wu and Jiwei Li. 2020. A Unified MRC Framework for Named Entity Recognition. In ACL."},{"key":"e_1_3_2_2_17_1","volume-title":"FLAT: Chinese NER Using Flat-Lattice Transformer. In 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."},{"key":"e_1_3_2_2_18_1","volume-title":"Online Indices for Predictive Top-k Entity and Aggregate Queries on Knowledge Graphs. In 2020 IEEE 36th International Conference on Data Engineering (ICDE). 1057--1068","author":"Li Yan","year":"2020","unstructured":"Yan Li, Tingjian Ge, and Cindy Chen. 2020. Online Indices for Predictive Top-k Entity and Aggregate Queries on Knowledge Graphs. In 2020 IEEE 36th International Conference on Data Engineering (ICDE). 1057--1068."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"crossref","unstructured":"Wei Liu Xiyan Fu Yue Zhang and Wenming Xiao. 2021. Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapter. In ACL\/IJCNLP.","DOI":"10.18653\/v1\/2021.acl-long.454"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","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.","DOI":"10.18653\/v1\/N19-1247"},{"key":"e_1_3_2_2_21_1","volume-title":"Swin transformer: Hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030","author":"Liu Ze","year":"2021","unstructured":"Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. 2021. Swin transformer: Hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)."},{"key":"e_1_3_2_2_22_1","unstructured":"Jiasen Lu Dhruv Batra Devi Parikh and Stefan Lee. 2019. ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks. In NeurIPS."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.340"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.01.005"},{"key":"e_1_3_2_2_25_1","unstructured":"Minlong Peng Ruotian Ma Qi Zhang and Xuanjing Huang. 2020. Simplify the Usage of Lexicon in Chinese NER. In ACL."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Nanyun Peng and Mark Dredze. 2015. Named Entity Recognition for Chinese Social Media with Jointly Trained Embeddings. In EMNLP. https:\/\/doi.org\/10. 18653\/v1\/d15--1064","DOI":"10.18653\/v1\/D15-1064"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Ying Shen Desi Wen Yaliang Li Nan Du Haitao Zheng and Min Yang. 2019. Path-based Attribute-aware Representation Learning for Relation Prediction. In SDM.","DOI":"10.1137\/1.9781611975673.72"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"crossref","unstructured":"C. Song and Arijit Sehanobish. 2020. Using Chinese Glyphs for Named Entity Recognition (Student Abstract). In AAAI.","DOI":"10.1609\/aaai.v34i10.7233"},{"key":"e_1_3_2_2_30_1","volume-title":"VideoBERT: A Joint Model for Video and Language Representation Learning. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), 7463--7472","author":"Sun Chen","unstructured":"Chen Sun, Austin Myers, Carl Vondrick, K. Murphy, and C. Schmid. 2019. VideoBERT: A Joint Model for Video and Language Representation Learning. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), 7463--7472."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","unstructured":"Zijun Sun Xiaoya Li Xiaofei Sun Yuxian Meng Xiang Ao Qing He Fei Wu and Jiwei Li. 2021. ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information. In ACL\/IJCNLP.","DOI":"10.18653\/v1\/2021.acl-long.161"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"crossref","unstructured":"Hao Tan and Mohit Bansal. 2019. LXMERT: Learning Cross-Modality Encoder Representations from Transformers. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics Hong Kong China 5100--5111. https:\/\/doi.org\/10. 18653\/v1\/D19--1514","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_3_2_2_33_1","unstructured":"Ashish Vaswani Noam M. Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. ArXiv abs\/1706.03762."},{"key":"e_1_3_2_2_34_1","volume-title":"Improving clinical named entity recognition in Chinese using the graphical and phonetic feature. BMC Medical Informatics and Decision Making 19","author":"Wang Yifei","year":"2019","unstructured":"Yifei Wang, S. Ananiadou, and Junichi Tsujii. 2019. Improving clinical named entity recognition in Chinese using the graphical and phonetic feature. BMC Medical Informatics and Decision Making 19 (2019)."},{"key":"e_1_3_2_2_35_1","volume-title":"LDC2011T03","author":"Weischedel Ralph","year":"2011","unstructured":"Ralph Weischedel, Sameer Pradhan, Lance Ramshaw, Martha Palmer, Nianwen Xue, Mitchell Marcus, Ann Taylor, Craig Greenberg, Eduard Hovy, Robert Belvin, et al. 2011. Ontonotes release 4.0. LDC2011T03, Philadelphia, Penn.: Linguistic Data Consortium (2011)."},{"key":"e_1_3_2_2_36_1","volume-title":"Glyce: Glyph-vectors for Chinese Character Representations. In NeurIPS.","author":"Wu Wei","year":"2019","unstructured":"Wei Wu, Yuxian Meng, F. Wang, Qinghong Han, Muyu Li, Xiaoya Li, J. Mei, Ping Nie, Xiaofei Sun, and Jiwei Li. 2019. Glyce: Glyph-vectors for Chinese Character Representations. In NeurIPS."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"Wei Ye B. Li Rui Xie Zhonghao Sheng Long Chen and Shikun Zhang. 2019. Exploiting Entity BIO Tag Embeddings and Multi-task Learning for Relation Extraction with Imbalanced Data. In ACL.","DOI":"10.18653\/v1\/P19-1130"},{"key":"e_1_3_2_2_38_1","unstructured":"Jianfei Yu Jing Jiang Li Yang and Rui Xia. 2020. Improving Multimodal Named Entity Recognition via Entity Span Detection with Unified Multimodal Transformer. In ACL."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107305"},{"key":"e_1_3_2_2_40_1","unstructured":"Suxiang Zhang Ying Qin JuanWen and XiaojieWang. 2006. Word Segmentation and Named Entity Recognition for SIGHAN Bakeoff3. In SIGHAN@COLING\/ACL."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1144"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1154"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3005952"}],"event":{"name":"WSDM '22: The Fifteenth ACM International Conference on Web Search and Data Mining","location":"Virtual Event AZ USA","acronym":"WSDM '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3488560.3498450","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3488560.3498450","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:31:18Z","timestamp":1750188678000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3488560.3498450"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,11]]},"references-count":43,"alternative-id":["10.1145\/3488560.3498450","10.1145\/3488560"],"URL":"https:\/\/doi.org\/10.1145\/3488560.3498450","relation":{},"subject":[],"published":{"date-parts":[[2022,2,11]]},"assertion":[{"value":"2022-02-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}