{"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/obtaining-better-static-word-embeddings-using","title":"Obtaining Better Static Word Embeddings Using Contextual Embedding Models","arxiv_id":"2106.04302","date":"2021-06-08","proceeding":"ACL 2021 5","authors":["Prakhar Gupta","Martin Jaggi"],"abstract":"The advent of contextual word embeddings -- representations of words which incorporate semantic and syntactic information from their context -- has led to tremendous improvements on a wide variety of NLP tasks. However, recent contextual models have prohibitively high computational cost in many use-cases and are often hard to interpret. In this work, we demonstrate that our proposed distillation method, which is a simple extension of CBOW-based training, allows to significantly improve computational efficiency of NLP applications, while outperforming the quality of existing static embeddings trained from scratch as well as those distilled from previously proposed methods. As a side-effect, our approach also allows a fair comparison of both contextual and static embeddings via standard lexical evaluation tasks.","url_abs":"https://arxiv.org/abs/2106.04302v1","url_pdf":"https://arxiv.org/pdf/2106.04302v1.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":"obtaining-better-static-word-embeddings-using","repo_url":"https://github.com/epfml/X2Static","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.04302","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04302"}},"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":"deterministic:regex_extraction","url":"https://github.com/epfml/X2Static","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":"d02277eba51f2f93","entry":"construct_dataset","repo":"epfml/X2Static","repo_kind":"official","path":"src/make_vocab_dataset.py","file_url":"https://github.com/epfml/X2Static/blob/HEAD/src/make_vocab_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d02277eba51f2f93"}},{"code_sha256_prefix":"c50a646c2d672bce","entry":"construct_vocab","repo":"epfml/X2Static","repo_kind":"official","path":"src/make_vocab_dataset.py","file_url":"https://github.com/epfml/X2Static/blob/HEAD/src/make_vocab_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c50a646c2d672bce"}},{"code_sha256_prefix":"107e21c6ef2a8b3b","entry":"ll_loss","repo":"epfml/X2Static","repo_kind":"official","path":"src/learn_from_bert_ver2.py","file_url":"https://github.com/epfml/X2Static/blob/HEAD/src/learn_from_bert_ver2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"107e21c6ef2a8b3b"}},{"code_sha256_prefix":"6b9085911cce0cd1","entry":"rejection_probs","repo":"epfml/X2Static","repo_kind":"official","path":"src/learn_from_bert_ver2.py","file_url":"https://github.com/epfml/X2Static/blob/HEAD/src/learn_from_bert_ver2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6b9085911cce0cd1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}