{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/hero-gang-neural-model-for-named-entity","title":"Hero-Gang Neural Model For Named Entity Recognition","arxiv_id":"2205.07177","date":"2022-05-15","proceeding":"NAACL 2022 7","authors":["Jinpeng Hu","Yaling Shen","Yang Liu","Xiang Wan","Tsung-Hui Chang"],"abstract":"Named entity recognition (NER) is a fundamental and important task in NLP, aiming at identifying named entities (NEs) from free text. Recently, since the multi-head attention mechanism applied in the Transformer model can effectively capture longer contextual information, Transformer-based models have become the mainstream methods and have achieved significant performance in this task. Unfortunately, although these models can capture effective global context information, they are still limited in the local feature and position information extraction, which is critical in NER. In this paper, to address this limitation, we propose a novel Hero-Gang Neural structure (HGN), including the Hero and Gang module, to leverage both global and local information to promote NER. Specifically, the Hero module is composed of a Transformer-based encoder to maintain the advantage of the self-attention mechanism, and the Gang module utilizes a multi-window recurrent module to extract local features and position information under the guidance of the Hero module. Afterward, the proposed multi-window attention effectively combines global information and multiple local features for predicting entity labels. Experimental results on several benchmark datasets demonstrate the effectiveness of our proposed model.","url_abs":"https://arxiv.org/abs/2205.07177v1","url_pdf":"https://arxiv.org/pdf/2205.07177v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"hero-gang-neural-model-for-named-entity","repo_url":"https://github.com/jinpeng01/hgn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cg","task_name":"NER"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":null,"task_name":"Position"},{"task_slug":"model","task_name":"model"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/named-entity-recognition-on-bc2gm","task":"Named Entity Recognition (NER)","dataset":"BC2GM","model":"HGN","rank_in_archive_order":5,"of":13,"metrics":{"F1":"85.65"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-on-bc5cdr-chemical","task":"Named Entity Recognition (NER)","dataset":"BC5CDR-chemical","model":"HGN","rank_in_archive_order":3,"of":13,"metrics":{"F1":"94.59"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-on-bc5cdr-disease","task":"Named Entity Recognition (NER)","dataset":"BC5CDR-disease","model":"HGN","rank_in_archive_order":2,"of":10,"metrics":{"F1":"87.86"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-on-ontonotes-5-0","task":"Named Entity Recognition (NER)","dataset":"OntoNotes 5.0","model":"HGN","rank_in_archive_order":1,"of":2,"metrics":{"Average F1":"90.92"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-ontonotes-v5","task":"Named Entity Recognition (NER)","dataset":"Ontonotes v5 (English)","model":"HGN","rank_in_archive_order":7,"of":28,"metrics":{"F1":"90.92"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-on-wnut-2016","task":"Named Entity Recognition (NER)","dataset":"WNUT 2016","model":"HGN","rank_in_archive_order":1,"of":7,"metrics":{"F1":"59.50"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-on-wnut-2017","task":"Named Entity Recognition (NER)","dataset":"WNUT 2017","model":"HGN","rank_in_archive_order":7,"of":23,"metrics":{"F1":"57.41"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.07177","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}