{"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/finding-function-in-form-compositional-1","title":"Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation","arxiv_id":"1508.02096","date":"2015-08-09","proceeding":"EMNLP 2015 9","authors":["Wang Ling","Tiago Luís","Luís Marujo","Ramón Fernandez Astudillo","Silvio Amir","Chris Dyer","Alan W. black","Isabel Trancoso"],"abstract":"We introduce a model for constructing vector representations of words by\ncomposing characters using bidirectional LSTMs. Relative to traditional word\nrepresentation models that have independent vectors for each word type, our\nmodel requires only a single vector per character type and a fixed set of\nparameters for the compositional model. Despite the compactness of this model\nand, more importantly, the arbitrary nature of the form-function relationship\nin language, our \"composed\" word representations yield state-of-the-art results\nin language modeling and part-of-speech tagging. Benefits over traditional\nbaselines are particularly pronounced in morphologically rich languages (e.g.,\nTurkish).","url_abs":"http://arxiv.org/abs/1508.02096v2","url_pdf":"http://arxiv.org/pdf/1508.02096v2.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":"finding-function-in-form-compositional-1","repo_url":"https://github.com/wlin12/JNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"form","task_name":"Form"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"part-of-speech-tagging","task_name":"Part-Of-Speech Tagging"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/part-of-speech-tagging-on-penn-treebank","task":"Part-Of-Speech Tagging","dataset":"Penn Treebank","model":"Char Bi-LSTM","rank_in_archive_order":4,"of":20,"metrics":{"Accuracy":"97.78"},"uses_additional_data":false},{"leaderboard":"/sota/part-of-speech-tagging-on-penn-treebank","task":"Part-Of-Speech Tagging","dataset":"Penn Treebank","model":"Bi-LSTM","rank_in_archive_order":17,"of":20,"metrics":{"Accuracy":"97.36"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1508.02096","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}