{"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/language-modeling-with-gated-convolutional","title":"Language Modeling with Gated Convolutional Networks","arxiv_id":"1612.08083","date":"2016-12-23","proceeding":"ICML 2017 8","authors":["Yann N. Dauphin","Angela Fan","Michael Auli","David Grangier"],"abstract":"The pre-dominant approach to language modeling to date is based on recurrent\nneural networks. Their success on this task is often linked to their ability to\ncapture unbounded context. In this paper we develop a finite context approach\nthrough stacked convolutions, which can be more efficient since they allow\nparallelization over sequential tokens. We propose a novel simplified gating\nmechanism that outperforms Oord et al (2016) and investigate the impact of key\narchitectural decisions. The proposed approach achieves state-of-the-art on the\nWikiText-103 benchmark, even though it features long-term dependencies, as well\nas competitive results on the Google Billion Words benchmark. Our model reduces\nthe latency to score a sentence by an order of magnitude compared to a\nrecurrent baseline. To our knowledge, this is the first time a non-recurrent\napproach is competitive with strong recurrent models on these large scale\nlanguage tasks.","url_abs":"http://arxiv.org/abs/1612.08083v3","url_pdf":"http://arxiv.org/pdf/1612.08083v3.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":"language-modeling-with-gated-convolutional","repo_url":"https://github.com/Rishit-dagli/GLU","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"language-modeling-with-gated-convolutional","repo_url":"https://github.com/astanway/gated-conv-nets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"language-modeling-with-gated-convolutional","repo_url":"https://github.com/facebookresearch/fairseq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"language-modeling-with-gated-convolutional","repo_url":"https://github.com/fangyiyu/Modified_MNIST_Classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"language-modeling-with-gated-convolutional","repo_url":"https://github.com/ibatra/nlm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"language-modeling-with-gated-convolutional","repo_url":"https://github.com/ifrit98/layer-glu","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"language-modeling-with-gated-convolutional","repo_url":"https://github.com/lxdragoon/Modified-mnist","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"language-modeling-with-gated-convolutional","repo_url":"https://github.com/mhagiwara/nanigonet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"language-modeling-with-gated-convolutional","repo_url":"https://github.com/pranav-ust/nlm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"language-modeling-with-gated-convolutional","repo_url":"https://github.com/selmiss/gp-tlstgcn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"language-modeling-with-gated-convolutional","repo_url":"https://github.com/stikbuf/Language_Modeling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"adaptive-softmax","method_name":"Adaptive Softmax"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"gated-convolution","method_name":"Gated Convolution"},{"method_slug":"gated-convolution-network","method_name":"Gated Convolution Network"},{"method_slug":"glu","method_name":"Gated Linear Unit"},{"method_slug":"gradient-clipping","method_name":"Gradient Clipping"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"nesterov-accelerated-gradient","method_name":"Nesterov Accelerated Gradient"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[{"slug":"gated-convolution-network","name":"Gated Convolution Network","full_name":"Gated Convolution Network"},{"slug":"glu","name":"Gated Linear Unit","full_name":"Gated Linear Unit"}],"results":[{"leaderboard":"/sota/language-modelling-on-one-billion-word","task":"Language Modelling","dataset":"One Billion Word","model":"GCNN-14 bottleneck","rank_in_archive_order":20,"of":27,"metrics":{"PPL":"31.9"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-wikitext-103","task":"Language Modelling","dataset":"WikiText-103","model":"GCNN-8","rank_in_archive_order":78,"of":89,"metrics":{"Test perplexity":"37.2","Validation perplexity":"-"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-wikitext-103","task":"Language Modelling","dataset":"WikiText-103","model":"GCNN-8","rank_in_archive_order":82,"of":89,"metrics":{"Test perplexity":"44.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1612.08083","atlas_url":"https://app.syntology.ai/?focus=1612.08083","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":"1612.08083"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1612.08083\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1612.08083"},"call":"get_concepts_for_paper(arxiv_id=\"1612.08083\")"}],"by_repo":[{"repo":"Rishit-dagli/GLU","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"astanway/gated-conv-nets","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"facebookresearch/fairseq","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"fangyiyu/Modified_MNIST_Classification","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ibatra/nlm","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ifrit98/layer-glu","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"lxdragoon/Modified-mnist","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"mhagiwara/nanigonet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"pranav-ust/nlm","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"selmiss/gp-tlstgcn","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["1606.09375","1609.02907"],"harvested_for_calls":[{"arxiv_id":"1606.09375","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1606.09375"},"call":"get_harvested_code_for_paper(arxiv_id=\"1606.09375\")"},{"arxiv_id":"1609.02907","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1609.02907"},"call":"get_harvested_code_for_paper(arxiv_id=\"1609.02907\")"}]},{"repo":"stikbuf/Language_Modeling","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"66a81c999f0d55d0e344d6d527aeba7cf376506f06e7ac599b95a3c6249fbc35","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}