{"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/hybrid-semi-markov-crf-for-neural-sequence","title":"Hybrid semi-Markov CRF for Neural Sequence Labeling","arxiv_id":"1805.03838","date":"2018-05-10","proceeding":"ACL 2018 7","authors":["Zhi-Xiu Ye","Zhen-Hua Ling"],"abstract":"This paper proposes hybrid semi-Markov conditional random fields (SCRFs) for\nneural sequence labeling in natural language processing. Based on conventional\nconditional random fields (CRFs), SCRFs have been designed for the tasks of\nassigning labels to segments by extracting features from and describing\ntransitions between segments instead of words. In this paper, we improve the\nexisting SCRF methods by employing word-level and segment-level information\nsimultaneously. First, word-level labels are utilized to derive the segment\nscores in SCRFs. Second, a CRF output layer and an SCRF output layer are\nintegrated into an unified neural network and trained jointly. Experimental\nresults on CoNLL 2003 named entity recognition (NER) shared task show that our\nmodel achieves state-of-the-art performance when no external knowledge is used.","url_abs":"http://arxiv.org/abs/1805.03838v1","url_pdf":"http://arxiv.org/pdf/1805.03838v1.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":"hybrid-semi-markov-crf-for-neural-sequence","repo_url":"https://github.com/ZhixiuYe/HSCRF-pytorch","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":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[{"method_slug":"crf","method_name":"CRF"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/named-entity-recognition-ner-on-conll-2003","task":"Named Entity Recognition (NER)","dataset":"CoNLL 2003 (English)","model":"HSCRF","rank_in_archive_order":62,"of":73,"metrics":{"F1":"91.38"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.03838","atlas_url":"https://app.syntology.ai/?focus=1805.03838","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}