{"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/understanding-composition-of-word-embeddings","title":"Understanding Composition of Word Embeddings via Tensor Decomposition","arxiv_id":"1902.00613","date":"2019-02-02","proceeding":"ICLR 2019 5","authors":["Abraham Frandsen","Rong Ge"],"abstract":"Word embedding is a powerful tool in natural language processing. In this\npaper we consider the problem of word embedding composition \\--- given vector\nrepresentations of two words, compute a vector for the entire phrase. We give a\ngenerative model that can capture specific syntactic relations between words.\nUnder our model, we prove that the correlations between three words (measured\nby their PMI) form a tensor that has an approximate low rank Tucker\ndecomposition. The result of the Tucker decomposition gives the word embeddings\nas well as a core tensor, which can be used to produce better compositions of\nthe word embeddings. We also complement our theoretical results with\nexperiments that verify our assumptions, and demonstrate the effectiveness of\nthe new composition method.","url_abs":"http://arxiv.org/abs/1902.00613v1","url_pdf":"http://arxiv.org/pdf/1902.00613v1.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":"understanding-composition-of-word-embeddings","repo_url":"https://github.com/abefrandsen/syntactic-rand-walk","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"understanding-composition-of-word-embeddings","repo_url":"https://github.com/MindSpore-scientific-2/code-8/tree/main/rand_conv-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"tensor-decomposition","task_name":"Tensor Decomposition"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[{"method_slug":"tucker","method_name":"TuckER"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1902.00613","atlas_url":"https://app.syntology.ai/?focus=1902.00613","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.00613"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/MindSpore-scientific-2/code-8/tree/main/rand_conv-master","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/abefrandsen/syntactic-rand-walk","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"ec7977b6ec96dce1","entry":"chunker","repo":"abefrandsen/syntactic-rand-walk","repo_kind":"official","path":"train_from_triplecounts.py","file_url":"https://github.com/abefrandsen/syntactic-rand-walk/blob/HEAD/train_from_triplecounts.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ec7977b6ec96dce1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}