{"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/learning-to-understand-phrases-by-embedding","title":"Learning to Understand Phrases by Embedding the Dictionary","arxiv_id":"1504.00548","date":"2015-04-02","proceeding":"TACL 2016 1","authors":["Felix Hill","Kyunghyun Cho","Anna Korhonen","Yoshua Bengio"],"abstract":"Distributional models that learn rich semantic word representations are a\nsuccess story of recent NLP research. However, developing models that learn\nuseful representations of phrases and sentences has proved far harder. We\npropose using the definitions found in everyday dictionaries as a means of\nbridging this gap between lexical and phrasal semantics. Neural language\nembedding models can be effectively trained to map dictionary definitions\n(phrases) to (lexical) representations of the words defined by those\ndefinitions. We present two applications of these architectures: \"reverse\ndictionaries\" that return the name of a concept given a definition or\ndescription and general-knowledge crossword question answerers. On both tasks,\nneural language embedding models trained on definitions from a handful of\nfreely-available lexical resources perform as well or better than existing\ncommercial systems that rely on significant task-specific engineering. The\nresults highlight the effectiveness of both neural embedding architectures and\ndefinition-based training for developing models that understand phrases and\nsentences.","url_abs":"http://arxiv.org/abs/1504.00548v4","url_pdf":"http://arxiv.org/pdf/1504.00548v4.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":"learning-to-understand-phrases-by-embedding","repo_url":"https://github.com/F-Almeman/GEAR_RD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-to-understand-phrases-by-embedding","repo_url":"https://github.com/northanapon/dict-definition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"learning-to-understand-phrases-by-embedding","repo_url":"https://github.com/thunlp/MultiRD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"general-knowledge","task_name":"General Knowledge"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1504.00548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1504.00548"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/F-Almeman/GEAR_RD","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thunlp/MultiRD","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/northanapon/dict-definition","reach":null}],"summary":{"unverified":6},"by_repo_kind":{"listed":{"samples":6,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"189bc681f75922bb","entry":"build_sentence_numpy","repo":"thunlp/MultiRD","repo_kind":"listed","path":"ChineseReverseDictionary/code/data.py","file_url":"https://github.com/thunlp/MultiRD/blob/HEAD/ChineseReverseDictionary/code/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"189bc681f75922bb"}},{"code_sha256_prefix":"097ad2cea688e3d9","entry":"evaluate","repo":"thunlp/MultiRD","repo_kind":"listed","path":"ChineseReverseDictionary/code/evaluate.py","file_url":"https://github.com/thunlp/MultiRD/blob/HEAD/ChineseReverseDictionary/code/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"097ad2cea688e3d9"}},{"code_sha256_prefix":"f4ccf34f650ff227","entry":"evaluate_test","repo":"thunlp/MultiRD","repo_kind":"listed","path":"ChineseReverseDictionary/code/evaluate.py","file_url":"https://github.com/thunlp/MultiRD/blob/HEAD/ChineseReverseDictionary/code/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f4ccf34f650ff227"}},{"code_sha256_prefix":"fb19e15c86dfad22","entry":"label_multihot","repo":"thunlp/MultiRD","repo_kind":"listed","path":"ChineseReverseDictionary/code/data.py","file_url":"https://github.com/thunlp/MultiRD/blob/HEAD/ChineseReverseDictionary/code/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fb19e15c86dfad22"}},{"code_sha256_prefix":"938c2f50b779ab0f","entry":"load_data","repo":"thunlp/MultiRD","repo_kind":"listed","path":"ChineseReverseDictionary/code/data.py","file_url":"https://github.com/thunlp/MultiRD/blob/HEAD/ChineseReverseDictionary/code/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"938c2f50b779ab0f"}},{"code_sha256_prefix":"26f1ce7a3aef5a8e","entry":"load_filterlist","repo":"thunlp/MultiRD","repo_kind":"listed","path":"PrepareYourOwnDataset/get_wordnet_500sample.py","file_url":"https://github.com/thunlp/MultiRD/blob/HEAD/PrepareYourOwnDataset/get_wordnet_500sample.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"26f1ce7a3aef5a8e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}