{"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/exploring-segment-representations-for-neural","title":"Exploring Segment Representations for Neural Segmentation Models","arxiv_id":"1604.05499","date":"2016-04-19","proceeding":null,"authors":["Yijia Liu","Wanxiang Che","Jiang Guo","Bing Qin","Ting Liu"],"abstract":"Many natural language processing (NLP) tasks can be generalized into\nsegmentation problem. In this paper, we combine semi-CRF with neural network to\nsolve NLP segmentation tasks. Our model represents a segment both by composing\nthe input units and embedding the entire segment. We thoroughly study different\ncomposition functions and different segment embeddings. We conduct extensive\nexperiments on two typical segmentation tasks: named entity recognition (NER)\nand Chinese word segmentation (CWS). Experimental results show that our neural\nsemi-CRF model benefits from representing the entire segment and achieves the\nstate-of-the-art performance on CWS benchmark dataset and competitive results\non the CoNLL03 dataset.","url_abs":"http://arxiv.org/abs/1604.05499v1","url_pdf":"http://arxiv.org/pdf/1604.05499v1.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":"exploring-segment-representations-for-neural","repo_url":"https://github.com/ExpResults/segrep-for-nn-semicrf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"chinese-word-segmentation","task_name":"Chinese Word Segmentation"},{"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":"segmentation","task_name":"Segmentation"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1604.05499","atlas_url":"https://app.syntology.ai/?focus=1604.05499","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}