{"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/neural-models-for-sequence-chunking","title":"Neural Models for Sequence Chunking","arxiv_id":"1701.04027","date":"2017-01-15","proceeding":null,"authors":["Feifei Zhai","Saloni Potdar","Bing Xiang","Bo-Wen Zhou"],"abstract":"Many natural language understanding (NLU) tasks, such as shallow parsing\n(i.e., text chunking) and semantic slot filling, require the assignment of\nrepresentative labels to the meaningful chunks in a sentence. Most of the\ncurrent deep neural network (DNN) based methods consider these tasks as a\nsequence labeling problem, in which a word, rather than a chunk, is treated as\nthe basic unit for labeling. These chunks are then inferred by the standard IOB\n(Inside-Outside-Beginning) labels. In this paper, we propose an alternative\napproach by investigating the use of DNN for sequence chunking, and propose\nthree neural models so that each chunk can be treated as a complete unit for\nlabeling. Experimental results show that the proposed neural sequence chunking\nmodels can achieve start-of-the-art performance on both the text chunking and\nslot filling tasks.","url_abs":"http://arxiv.org/abs/1701.04027v1","url_pdf":"http://arxiv.org/pdf/1701.04027v1.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":"neural-models-for-sequence-chunking","repo_url":"https://github.com/threelittlemonkeys/pointer-network-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"chunking","task_name":"Chunking"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"slot-filling","task_name":"Slot Filling"},{"task_slug":"slot-filling-1","task_name":"slot-filling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1701.04027","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}