{"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/entity-identification-as-multitasking","title":"Entity Identification as Multitasking","arxiv_id":"1612.02706","date":"2016-12-08","proceeding":"WS 2017 9","authors":["Karl Stratos"],"abstract":"Standard approaches in entity identification hard-code boundary detection and\ntype prediction into labels (e.g., John/B-PER Smith/I-PER) and then perform\nViterbi. This has two disadvantages: 1. the runtime complexity grows\nquadratically in the number of types, and 2. there is no natural segment-level\nrepresentation. In this paper, we propose a novel neural architecture that\naddresses these disadvantages. We frame the problem as multitasking, separating\nboundary detection and type prediction but optimizing them jointly. Despite its\nsimplicity, this architecture performs competitively with fully structured\nmodels such as BiLSTM-CRFs while scaling linearly in the number of types.\nFurthermore, by construction, the model induces type-disambiguating embeddings\nof predicted mentions.","url_abs":"http://arxiv.org/abs/1612.02706v2","url_pdf":"http://arxiv.org/pdf/1612.02706v2.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":"entity-identification-as-multitasking","repo_url":"https://github.com/karlstratos/mention2vec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"boundary-detection","task_name":"Boundary Detection"},{"task_slug":"type-prediction","task_name":"Type prediction"},{"task_slug":"type","task_name":"Vocal Bursts Type Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1612.02706","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}