{"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/adaptive-attention-span-in-transformers","title":"Adaptive Attention Span in Transformers","arxiv_id":"1905.07799","date":"2019-05-19","proceeding":"ACL 2019 7","authors":["Sainbayar Sukhbaatar","Edouard Grave","Piotr Bojanowski","Armand Joulin"],"abstract":"We propose a novel self-attention mechanism that can learn its optimal attention span. This allows us to extend significantly the maximum context size used in Transformer, while maintaining control over their memory footprint and computational time. We show the effectiveness of our approach on the task of character level language modeling, where we achieve state-of-the-art performances on text8 and enwiki8 by using a maximum context of 8k characters.","url_abs":"https://arxiv.org/abs/1905.07799v2","url_pdf":"https://arxiv.org/pdf/1905.07799v2.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":"adaptive-attention-span-in-transformers","repo_url":"https://github.com/facebookresearch/adaptive-span","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"adaptive-attention-span-in-transformers","repo_url":"https://github.com/JoeRoussy/adaptive-attention-in-cv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"adaptive-attention-span-in-transformers","repo_url":"https://github.com/jerrodparker20/adaptive-transformers-in-rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"adaptive-attention-span-in-transformers","repo_url":"https://github.com/lancopku/Explicit-Sparse-Transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"adaptive-attention-span-in-transformers","repo_url":"https://github.com/ofirpress/sandwich_transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"adaptive-attention-span-in-transformers","repo_url":"https://github.com/prajjwal1/adaptive_transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"adaptive-attention-span-in-transformers","repo_url":"https://github.com/prajjwal1/fluence","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"adaptive-attention-span-in-transformers","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/7/Knowing-When-to-Look-Adaptive-Attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":null,"task_name":"8k"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"adaptive-masking","method_name":"Adaptive Masking"},{"method_slug":"adaptive-span-transformer","method_name":"Adaptive Span Transformer"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"embedding-dropout","method_name":"Embedding Dropout"},{"method_slug":"l1-regularization","method_name":"L1 Regularization"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/language-modelling-on-text8","task":"Language Modelling","dataset":"Text8","model":"24L Transformer + 8K adaptive span","rank_in_archive_order":4,"of":24,"metrics":{"Bit per Character (BPC)":"1.07","Number of params":"209M"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-text8","task":"Language Modelling","dataset":"Text8","model":"12L Transformer + 8K adaptive span","rank_in_archive_order":8,"of":24,"metrics":{"Bit per Character (BPC)":"1.11","Number of params":"38M"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-enwiki8","task":"Language Modelling","dataset":"enwik8","model":"Transformer (24 layers, 8k adaptive span)","rank_in_archive_order":11,"of":42,"metrics":{"Bit per Character (BPC)":"0.98","Number of params":"209M"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-enwiki8","task":"Language Modelling","dataset":"enwik8","model":"Transformer (12 layers, 8k adaptive span)","rank_in_archive_order":20,"of":42,"metrics":{"Bit per Character (BPC)":"1.02","Number of params":"39M"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1905.07799","atlas_url":"https://app.syntology.ai/?focus=1905.07799","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":"1905.07799"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1905.07799\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1905.07799"},"call":"get_concepts_for_paper(arxiv_id=\"1905.07799\")"}],"by_repo":[{"repo":"facebookresearch/adaptive-span","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"JoeRoussy/adaptive-attention-in-cv","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1906.05909"],"harvested_for_calls":[{"arxiv_id":"1906.05909","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1906.05909"},"call":"get_harvested_code_for_paper(arxiv_id=\"1906.05909\")"}]},{"repo":"jerrodparker20/adaptive-transformers-in-rl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"lancopku/Explicit-Sparse-Transformer","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ofirpress/sandwich_transformer","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"prajjwal1/adaptive_transformer","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"prajjwal1/fluence","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1909.00015"],"harvested_for_calls":[{"arxiv_id":"1909.00015","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1909.00015"},"call":"get_harvested_code_for_paper(arxiv_id=\"1909.00015\")"}]},{"repo":"pwc-1/Paper-9","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1909.13719"],"harvested_for_calls":[{"arxiv_id":"1909.13719","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1909.13719"},"call":"get_harvested_code_for_paper(arxiv_id=\"1909.13719\")"}]}],"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":"c359ab2685c35d8832a58f3f6866c351ac83283f5809fb6d23b5ba4d4d88edce","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}