{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/linear-algebraic-structure-of-word-senses","title":"Linear Algebraic Structure of Word Senses, with Applications to Polysemy","arxiv_id":"1601.03764","date":"2016-01-14","proceeding":"TACL 2018 1","authors":["Sanjeev Arora","Yuanzhi Li","YIngyu Liang","Tengyu Ma","Andrej Risteski"],"abstract":"Word embeddings are ubiquitous in NLP and information retrieval, but it is\nunclear what they represent when the word is polysemous. Here it is shown that\nmultiple word senses reside in linear superposition within the word embedding\nand simple sparse coding can recover vectors that approximately capture the\nsenses. The success of our approach, which applies to several embedding\nmethods, is mathematically explained using a variant of the random walk on\ndiscourses model (Arora et al., 2016). A novel aspect of our technique is that\neach extracted word sense is accompanied by one of about 2000 \"discourse atoms\"\nthat gives a succinct description of which other words co-occur with that word\nsense. Discourse atoms can be of independent interest, and make the method\npotentially more useful. Empirical tests are used to verify and support the\ntheory.","url_abs":"http://arxiv.org/abs/1601.03764v6","url_pdf":"http://arxiv.org/pdf/1601.03764v6.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":"linear-algebraic-structure-of-word-senses","repo_url":"https://github.com/PrincetonML/SemanticVector","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1601.03764","atlas_url":"https://app.syntology.ai/?focus=1601.03764","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1601.03764"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1601.03764\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1601.03764"},"call":"get_concepts_for_paper(arxiv_id=\"1601.03764\")"}],"by_repo":[{"repo":"PrincetonML/SemanticVector","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"cb185075c07a5f882d44acfe9beb5e7166d14139d87f09c3806c2bd09cae0917","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}