{"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/using-the-output-embedding-to-improve","title":"Using the Output Embedding to Improve Language Models","arxiv_id":"1608.05859","date":"2016-08-20","proceeding":"EACL 2017 4","authors":["Ofir Press","Lior Wolf"],"abstract":"We study the topmost weight matrix of neural network language models. We show\nthat this matrix constitutes a valid word embedding. When training language\nmodels, we recommend tying the input embedding and this output embedding. We\nanalyze the resulting update rules and show that the tied embedding evolves in\na more similar way to the output embedding than to the input embedding in the\nuntied model. We also offer a new method of regularizing the output embedding.\nOur methods lead to a significant reduction in perplexity, as we are able to\nshow on a variety of neural network language models. Finally, we show that\nweight tying can reduce the size of neural translation models to less than half\nof their original size without harming their performance.","url_abs":"http://arxiv.org/abs/1608.05859v3","url_pdf":"http://arxiv.org/pdf/1608.05859v3.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":"using-the-output-embedding-to-improve","repo_url":"https://github.com/ofirpress/UsingTheOutputEmbedding","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"using-the-output-embedding-to-improve","repo_url":"https://github.com/BugOMan/summary_generator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"using-the-output-embedding-to-improve","repo_url":"https://github.com/JeffreyJosanne/nematus_tf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"using-the-output-embedding-to-improve","repo_url":"https://github.com/arijitthegame/hybrid-sampling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"using-the-output-embedding-to-improve","repo_url":"https://github.com/bhaddow/dev-nematus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"using-the-output-embedding-to-improve","repo_url":"https://github.com/faramarzmunshi/d2l-nlp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"using-the-output-embedding-to-improve","repo_url":"https://github.com/floydhub/word-language-model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"using-the-output-embedding-to-improve","repo_url":"https://github.com/jiali-ms/JLM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"using-the-output-embedding-to-improve","repo_url":"https://github.com/lium-lst/nmtpy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"using-the-output-embedding-to-improve","repo_url":"https://github.com/zhangyaoyuan/GAN-Simplification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"translation","task_name":"Translation"},{"task_slug":null,"task_name":"valid"}],"methods":[{"method_slug":"weight-tying","method_name":"Weight Tying"}],"datasets_introduced":[],"methods_introduced":[{"slug":"weight-tying","name":"Weight Tying","full_name":"Weight Tying"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1608.05859","atlas_url":"https://app.syntology.ai/?focus=1608.05859","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":"1608.05859"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1608.05859\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1608.05859"},"call":"get_concepts_for_paper(arxiv_id=\"1608.05859\")"}],"by_repo":[{"repo":"ofirpress/UsingTheOutputEmbedding","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"BugOMan/summary_generator","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"JeffreyJosanne/nematus_tf","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1607.06450"],"harvested_for_calls":[{"arxiv_id":"1607.06450","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1607.06450"},"call":"get_harvested_code_for_paper(arxiv_id=\"1607.06450\")"}]},{"repo":"arijitthegame/hybrid-sampling","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2110.04367"],"harvested_for_calls":[{"arxiv_id":"2110.04367","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2110.04367"},"call":"get_harvested_code_for_paper(arxiv_id=\"2110.04367\")"}]},{"repo":"bhaddow/dev-nematus","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1607.06450"],"harvested_for_calls":[{"arxiv_id":"1607.06450","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1607.06450"},"call":"get_harvested_code_for_paper(arxiv_id=\"1607.06450\")"}]},{"repo":"faramarzmunshi/d2l-nlp","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"floydhub/word-language-model","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jiali-ms/JLM","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1510.00149"],"harvested_for_calls":[{"arxiv_id":"1510.00149","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1510.00149"},"call":"get_harvested_code_for_paper(arxiv_id=\"1510.00149\")"}]},{"repo":"lium-lst/nmtpy","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"zhangyaoyuan/GAN-Simplification","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1607.06450"],"harvested_for_calls":[{"arxiv_id":"1607.06450","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1607.06450"},"call":"get_harvested_code_for_paper(arxiv_id=\"1607.06450\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"45c55b4891e54bc4c774877caee9c54d3c826b2280954d117a1a1ca9470ad6be","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}