{"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/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":{"atlas_url":"https://app.syntology.ai/?focus=1612.08083","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}