{"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/hierarchically-refined-label-attention","title":"Hierarchically-Refined Label Attention Network for Sequence Labeling","arxiv_id":"1908.08676","date":"2019-08-23","proceeding":"IJCNLP 2019 11","authors":["Leyang Cui","Yue Zhang"],"abstract":"CRF has been used as a powerful model for statistical sequence labeling. For neural sequence labeling, however, BiLSTM-CRF does not always lead to better results compared with BiLSTM-softmax local classification. This can be because the simple Markov label transition model of CRF does not give much information gain over strong neural encoding. For better representing label sequences, we investigate a hierarchically-refined label attention network, which explicitly leverages label embeddings and captures potential long-term label dependency by giving each word incrementally refined label distributions with hierarchical attention. Results on POS tagging, NER and CCG supertagging show that the proposed model not only improves the overall tagging accuracy with similar number of parameters, but also significantly speeds up the training and testing compared to BiLSTM-CRF.","url_abs":"https://arxiv.org/abs/1908.08676v3","url_pdf":"https://arxiv.org/pdf/1908.08676v3.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":"hierarchically-refined-label-attention","repo_url":"https://github.com/Nealcly/LAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"hierarchically-refined-label-attention","repo_url":"https://github.com/Nealcly/BiLSTM-LAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"ccg-supertagging","task_name":"CCG Supertagging"},{"task_slug":"cg","task_name":"NER"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"pos","task_name":"POS"},{"task_slug":"pos-tagging","task_name":"POS Tagging"},{"task_slug":"part-of-speech-tagging","task_name":"Part-Of-Speech Tagging"}],"methods":[{"method_slug":"crf","method_name":"CRF"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/ccg-supertagging-on-ccgbank","task":"CCG Supertagging","dataset":"CCGbank","model":"BiLSTM-LAN","rank_in_archive_order":5,"of":8,"metrics":{"Accuracy":"94.7"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-ontonotes-v5","task":"Named Entity Recognition (NER)","dataset":"Ontonotes v5 (English)","model":"BiLSTM-LAN","rank_in_archive_order":21,"of":28,"metrics":{"F1":"88.16"},"uses_additional_data":false},{"leaderboard":"/sota/part-of-speech-tagging-on-penn-treebank","task":"Part-Of-Speech Tagging","dataset":"Penn Treebank","model":"BiLSTM-LAN","rank_in_archive_order":7,"of":20,"metrics":{"Accuracy":"97.65"},"uses_additional_data":false},{"leaderboard":"/sota/part-of-speech-tagging-on-ud","task":"Part-Of-Speech Tagging","dataset":"UD","model":"BiLSTM-LAN","rank_in_archive_order":1,"of":5,"metrics":{"Avg accuracy":"96.88"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1908.08676","atlas_url":"https://app.syntology.ai/?focus=1908.08676","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}