{"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":"/method/adaptive-span-transformer","slug":"adaptive-span-transformer","name":"Adaptive Span Transformer","full_name":"Adaptive Span Transformer","full_name_withheld":false,"description_markdown":"The **Adaptive Attention Span Transformer** is a Transformer that utilises an improvement to the self-attention layer called [adaptive masking](https://paperswithcode.com/method/adaptive-masking) that allows the model to choose its own context size. This results in a network where each attention layer gathers information on their own context. This allows for scaling to input sequences of more than 8k tokens.\r\n\r\nTheir proposals are based on the observation that, with the dense attention of a traditional [Transformer](https://paperswithcode.com/method/transformer), each attention head shares the same attention span $S$ (attending over the full context). But many attention heads can specialize to more local context (others look at the longer sequence). This motivates the need for a variant of self-attention that allows the model to choose its own context size (adaptive masking - see components).","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/1905.07799v2","title":"Adaptive Attention Span in Transformers","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Transformers","url":"/methods/category/transformers","pwc_aliases":[]}],"n_papers_tagged":3,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/self-attention-between-datapoints-going","slug":"self-attention-between-datapoints-going","title":"Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning","date":"2021-06-04","arxiv_id":"2106.02584","n_code_links":3,"syntology":{"ran":22,"of":30,"n_ran_checked":20,"n_instrument":2,"unverified":8,"pointer_only":0,"phrase":"22 ran (of which 4 constructed an object rather than computing a result; 20 with no instrument failure: 2 honoured, 1 violated, 17 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","official":{"repos":["OATML/Non-Parametric-Transformers"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/improving-transformer-models-by-reordering","slug":"improving-transformer-models-by-reordering","title":"Improving Transformer Models by Reordering their Sublayers","date":"2019-11-10","arxiv_id":"1911.03864","n_code_links":2,"syntology":null},{"paper":"/paper/adaptive-attention-span-in-transformers","slug":"adaptive-attention-span-in-transformers","title":"Adaptive Attention Span in Transformers","date":"2019-05-19","arxiv_id":"1905.07799","n_code_links":8,"syntology":null}],"papers_shown":3,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":3,"with_a_code_link":3,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":3,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/method/adaptive-span-transformer/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/adaptive-span-transformer/papers/ran/1","json":"/method/adaptive-span-transformer/papers/ran/1.json","rows":1}],"tasks":[{"task":"/task/language-modeling","name":"Language Modeling","papers":2},{"task":"/task/language-modelling","name":"Language Modelling","papers":2},{"task":"/task/3d-part-segmentation","name":"3D Part Segmentation","papers":1},{"task":null,"name":"8k","papers":1},{"task":"/task/deep-learning","name":"Deep Learning","papers":1},{"task":"/task/machine-translation","name":"Machine Translation","papers":1},{"task":"/task/translation","name":"Translation","papers":1}],"tasks_shown":7,"n_tasks":7,"usage_by_year":[{"year":"2019","papers":2},{"year":"2021","papers":1}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/adaptive-span-transformer"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Adaptive%20Span%20Transformer","read_at":"2026-10-05T00:51:35+00:00","query":"Adaptive Span Transformer","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":null,"repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'Adaptive Span Transformer' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["SPAN","Span-Fact","Transformer","Span-ConveRT","L-Transformer","G-Transformer","CK-Transformer","span attention"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"7ef602f75f27dc73a3faea7f70767ceca1135d3cf85f0a15b6a5ad87b936c011","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}