{"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/diachronic-word-embeddings-reveal-statistical","title":"Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change","arxiv_id":"1605.09096","date":"2016-05-30","proceeding":"ACL 2016 8","authors":["William L. Hamilton","Jure Leskovec","Dan Jurafsky"],"abstract":"Understanding how words change their meanings over time is key to models of\nlanguage and cultural evolution, but historical data on meaning is scarce,\nmaking theories hard to develop and test. Word embeddings show promise as a\ndiachronic tool, but have not been carefully evaluated. We develop a robust\nmethodology for quantifying semantic change by evaluating word embeddings\n(PPMI, SVD, word2vec) against known historical changes. We then use this\nmethodology to reveal statistical laws of semantic evolution. Using six\nhistorical corpora spanning four languages and two centuries, we propose two\nquantitative laws of semantic change: (i) the law of conformity---the rate of\nsemantic change scales with an inverse power-law of word frequency; (ii) the\nlaw of innovation---independent of frequency, words that are more polysemous\nhave higher rates of semantic change.","url_abs":"http://arxiv.org/abs/1605.09096v6","url_pdf":"http://arxiv.org/pdf/1605.09096v6.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":"diachronic-word-embeddings-reveal-statistical","repo_url":"https://github.com/Ahren09/dygetviz","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"diachronic-word-embeddings-reveal-statistical","repo_url":"https://github.com/MLBurnham/word_embeddings","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"diachronic-word-embeddings-reveal-statistical","repo_url":"https://github.com/albertyusun/For-the-Love-of-Greed","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"diachronic-word-embeddings-reveal-statistical","repo_url":"https://github.com/claws-lab/dygetviz","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"diachronic-word-embeddings-reveal-statistical","repo_url":"https://github.com/network-embeddings/temporal_embedding_matching","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"diachronic-word-embeddings-reveal-statistical","repo_url":"https://github.com/williamleif/histwords","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"diachronic-word-embeddings","task_name":"Diachronic Word Embeddings"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1605.09096","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.09096"}},"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/network-embeddings/temporal_embedding_matching","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/williamleif/histwords","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/albertyusun/For-the-Love-of-Greed","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MLBurnham/word_embeddings","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/claws-lab/dygetviz","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Ahren09/dygetviz","reach":{"status":"ok"}}],"summary":{"unverified":8},"by_repo_kind":{"listed":{"samples":8,"ran":0,"repositories":2}},"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":"00d99d08ac61f19a","entry":"align_list_of_embs","repo":"network-embeddings/temporal_embedding_matching","repo_kind":"listed","path":"align_embs.py","file_url":"https://github.com/network-embeddings/temporal_embedding_matching/blob/HEAD/align_embs.py","link_basis":"harvester_set","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":"00d99d08ac61f19a"}},{"code_sha256_prefix":"8c86cccc3f85c086","entry":"align_two_embs","repo":"network-embeddings/temporal_embedding_matching","repo_kind":"listed","path":"align_embs.py","file_url":"https://github.com/network-embeddings/temporal_embedding_matching/blob/HEAD/align_embs.py","link_basis":"harvester_set","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":"8c86cccc3f85c086"}},{"code_sha256_prefix":"a01a035ff8870c96","entry":"clean_pos","repo":"williamleif/histwords","repo_kind":"listed","path":"coha/cohastringutils.py","file_url":"https://github.com/williamleif/histwords/blob/HEAD/coha/cohastringutils.py","link_basis":"harvester_set","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":"a01a035ff8870c96"}},{"code_sha256_prefix":"897b037a7b524b3c","entry":"clean_word_permissive","repo":"williamleif/histwords","repo_kind":"listed","path":"coha/cohastringutils.py","file_url":"https://github.com/williamleif/histwords/blob/HEAD/coha/cohastringutils.py","link_basis":"harvester_set","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":"897b037a7b524b3c"}},{"code_sha256_prefix":"185e114a33b53568","entry":"make_data_frame","repo":"williamleif/histwords","repo_kind":"listed","path":"statutils/mixedmodels.py","file_url":"https://github.com/williamleif/histwords/blob/HEAD/statutils/mixedmodels.py","link_basis":"harvester_set","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":"185e114a33b53568"}},{"code_sha256_prefix":"29c76d6ec4da6cc4","entry":"marginal_r2","repo":"williamleif/histwords","repo_kind":"listed","path":"statutils/mixedmodels.py","file_url":"https://github.com/williamleif/histwords/blob/HEAD/statutils/mixedmodels.py","link_basis":"harvester_set","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":"29c76d6ec4da6cc4"}},{"code_sha256_prefix":"41d3c7b00eb544c6","entry":"process_lemma_line","repo":"williamleif/histwords","repo_kind":"listed","path":"coha/cohastringutils.py","file_url":"https://github.com/williamleif/histwords/blob/HEAD/coha/cohastringutils.py","link_basis":"harvester_set","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":"41d3c7b00eb544c6"}},{"code_sha256_prefix":"4f9bed08d41f5491","entry":"run_lmm","repo":"williamleif/histwords","repo_kind":"listed","path":"statutils/mixedmodels.py","file_url":"https://github.com/williamleif/histwords/blob/HEAD/statutils/mixedmodels.py","link_basis":"harvester_set","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":"4f9bed08d41f5491"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}