{"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/compressing-word-embeddings-via-deep","title":"Compressing Word Embeddings via Deep Compositional Code Learning","arxiv_id":"1711.01068","date":"2017-11-03","proceeding":"ICLR 2018 1","authors":["Raphael Shu","Hideki Nakayama"],"abstract":"Natural language processing (NLP) models often require a massive number of\nparameters for word embeddings, resulting in a large storage or memory\nfootprint. Deploying neural NLP models to mobile devices requires compressing\nthe word embeddings without any significant sacrifices in performance. For this\npurpose, we propose to construct the embeddings with few basis vectors. For\neach word, the composition of basis vectors is determined by a hash code. To\nmaximize the compression rate, we adopt the multi-codebook quantization\napproach instead of binary coding scheme. Each code is composed of multiple\ndiscrete numbers, such as (3, 2, 1, 8), where the value of each component is\nlimited to a fixed range. We propose to directly learn the discrete codes in an\nend-to-end neural network by applying the Gumbel-softmax trick. Experiments\nshow the compression rate achieves 98% in a sentiment analysis task and 94% ~\n99% in machine translation tasks without performance loss. In both tasks, the\nproposed method can improve the model performance by slightly lowering the\ncompression rate. Compared to other approaches such as character-level\nsegmentation, the proposed method is language-independent and does not require\nmodifications to the network architecture.","url_abs":"http://arxiv.org/abs/1711.01068v2","url_pdf":"http://arxiv.org/pdf/1711.01068v2.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":"compressing-word-embeddings-via-deep","repo_url":"https://github.com/mingu600/compositional_code_learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"compressing-word-embeddings-via-deep","repo_url":"https://github.com/wang-h/neuralcompressor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"compressing-word-embeddings-via-deep","repo_url":"https://github.com/zomux/neuralcompressor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/machine-translation-on-iwslt2015-german","task":"Machine Translation","dataset":"IWSLT2015 German-English","model":"DCCL","rank_in_archive_order":10,"of":15,"metrics":{"BLEU score":"29.56"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.01068","atlas_url":"https://app.syntology.ai/?focus=1711.01068","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":"1711.01068"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1711.01068\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1711.01068"},"call":"get_concepts_for_paper(arxiv_id=\"1711.01068\")"}],"by_repo":[{"repo":"mingu600/compositional_code_learning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"wang-h/neuralcompressor","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"zomux/neuralcompressor","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":"671538e6770ce0557c11e41371c9a46820a965e4167b6284f1b4229295572252","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}