{"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/cbow-is-not-all-you-need-combining-cbow-with","title":"CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model","arxiv_id":"1902.06423","date":"2019-02-18","proceeding":"ICLR 2019 5","authors":["Florian Mai","Lukas Galke","Ansgar Scherp"],"abstract":"Continuous Bag of Words (CBOW) is a powerful text embedding method. Due to\nits strong capabilities to encode word content, CBOW embeddings perform well on\na wide range of downstream tasks while being efficient to compute. However,\nCBOW is not capable of capturing the word order. The reason is that the\ncomputation of CBOW's word embeddings is commutative, i.e., embeddings of XYZ\nand ZYX are the same. In order to address this shortcoming, we propose a\nlearning algorithm for the Continuous Matrix Space Model, which we call\nContinual Multiplication of Words (CMOW). Our algorithm is an adaptation of\nword2vec, so that it can be trained on large quantities of unlabeled text. We\nempirically show that CMOW better captures linguistic properties, but it is\ninferior to CBOW in memorizing word content. Motivated by these findings, we\npropose a hybrid model that combines the strengths of CBOW and CMOW. Our\nresults show that the hybrid CBOW-CMOW-model retains CBOW's strong ability to\nmemorize word content while at the same time substantially improving its\nability to encode other linguistic information by 8%. As a result, the hybrid\nalso performs better on 8 out of 11 supervised downstream tasks with an average\nimprovement of 1.2%.","url_abs":"http://arxiv.org/abs/1902.06423v1","url_pdf":"http://arxiv.org/pdf/1902.06423v1.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":"cbow-is-not-all-you-need-combining-cbow-with","repo_url":"https://github.com/florianmai/word2mat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1902.06423","atlas_url":"https://app.syntology.ai/?focus=1902.06423","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":"1902.06423"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1902.06423\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1902.06423"},"call":"get_concepts_for_paper(arxiv_id=\"1902.06423\")"}],"by_repo":[{"repo":"florianmai/word2mat","kind":"official","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":"a8982308f253e526d4f6cfe95fac1f4abdbbb1b5ae633965afbd7b6c8f670ad6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}