{"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/acceptability-judgements-via-examining-the","title":"Acceptability Judgements via Examining the Topology of Attention Maps","arxiv_id":"2205.09630","date":"2022-05-19","proceeding":null,"authors":["Daniil Cherniavskii","Eduard Tulchinskii","Vladislav Mikhailov","Irina Proskurina","Laida Kushnareva","Ekaterina Artemova","Serguei Barannikov","Irina Piontkovskaya","Dmitri Piontkovski","Evgeny Burnaev"],"abstract":"The role of the attention mechanism in encoding linguistic knowledge has received special interest in NLP. However, the ability of the attention heads to judge the grammatical acceptability of a sentence has been underexplored. This paper approaches the paradigm of acceptability judgments with topological data analysis (TDA), showing that the geometric properties of the attention graph can be efficiently exploited for two standard practices in linguistics: binary judgments and linguistic minimal pairs. Topological features enhance the BERT-based acceptability classifier scores by $8$%-$24$% on CoLA in three languages (English, Italian, and Swedish). By revealing the topological discrepancy between attention maps of minimal pairs, we achieve the human-level performance on the BLiMP benchmark, outperforming nine statistical and Transformer LM baselines. At the same time, TDA provides the foundation for analyzing the linguistic functions of attention heads and interpreting the correspondence between the graph features and grammatical phenomena.","url_abs":"https://arxiv.org/abs/2205.09630v2","url_pdf":"https://arxiv.org/pdf/2205.09630v2.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":"acceptability-judgements-via-examining-the","repo_url":"https://github.com/danchern97/tda4la","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"CoLA"},{"task_slug":"linguistic-acceptability","task_name":"Linguistic Acceptability"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"topological-data-analysis","task_name":"Topological Data Analysis"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cola","method_name":"COLA"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"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":"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/linguistic-acceptability-on-cola","task":"Linguistic Acceptability","dataset":"CoLA","model":"En-BERT + TDA + PCA","rank_in_archive_order":1,"of":43,"metrics":{"Accuracy":"88.6%"},"uses_additional_data":false},{"leaderboard":"/sota/linguistic-acceptability-on-cola","task":"Linguistic Acceptability","dataset":"CoLA","model":"En-BERT + TDA","rank_in_archive_order":8,"of":43,"metrics":{"Accuracy":"82.1%","MCC":"0.565"},"uses_additional_data":false},{"leaderboard":"/sota/linguistic-acceptability-on-cola-dev","task":"Linguistic Acceptability","dataset":"CoLA Dev","model":"En-BERT + TDA","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"88.6","MCC":"0.725"},"uses_additional_data":false},{"leaderboard":"/sota/linguistic-acceptability-on-cola-dev","task":"Linguistic Acceptability","dataset":"CoLA Dev","model":"XLM-R (pre-trained) + TDA","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy":"73"},"uses_additional_data":false},{"leaderboard":"/sota/linguistic-acceptability-on-cola-dev","task":"Linguistic Acceptability","dataset":"CoLA Dev","model":"En-BERT (pre-trained) + TDA","rank_in_archive_order":6,"of":6,"metrics":{"MCC":"0.420"},"uses_additional_data":false},{"leaderboard":"/sota/linguistic-acceptability-on-dalaj","task":"Linguistic Acceptability","dataset":"DaLAJ","model":"Sw-BERT + H0M","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"76.9","MCC":"0.542"},"uses_additional_data":false},{"leaderboard":"/sota/linguistic-acceptability-on-itacola","task":"Linguistic Acceptability","dataset":"ItaCoLA","model":"XLM-R + TDA","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"92.8","MCC":"0.683"},"uses_additional_data":false},{"leaderboard":"/sota/linguistic-acceptability-on-itacola","task":"Linguistic Acceptability","dataset":"ItaCoLA","model":"It-BERT (pre-trained) + TDA","rank_in_archive_order":3,"of":4,"metrics":{"Accuracy":"89.2","MCC":"0.478"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"danchern97/tda4la","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"7f0485eb59cfa195bc124d43b9691c3a662d1ccb910b3d87d16e6d495eebe4fd","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}