{"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/mate-multi-view-attention-for-table","title":"MATE: Multi-view Attention for Table Transformer Efficiency","arxiv_id":"2109.04312","date":"2021-09-09","proceeding":"EMNLP 2021 11","authors":["Julian Martin Eisenschlos","Maharshi Gor","Thomas Müller","William W. Cohen"],"abstract":"This work presents a sparse-attention Transformer architecture for modeling documents that contain large tables. Tables are ubiquitous on the web, and are rich in information. However, more than 20% of relational tables on the web have 20 or more rows (Cafarella et al., 2008), and these large tables present a challenge for current Transformer models, which are typically limited to 512 tokens. Here we propose MATE, a novel Transformer architecture designed to model the structure of web tables. MATE uses sparse attention in a way that allows heads to efficiently attend to either rows or columns in a table. This architecture scales linearly with respect to speed and memory, and can handle documents containing more than 8000 tokens with current accelerators. MATE also has a more appropriate inductive bias for tabular data, and sets a new state-of-the-art for three table reasoning datasets. For HybridQA (Chen et al., 2020b), a dataset that involves large documents containing tables, we improve the best prior result by 19 points.","url_abs":"https://arxiv.org/abs/2109.04312v1","url_pdf":"https://arxiv.org/pdf/2109.04312v1.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":"mate-multi-view-attention-for-table","repo_url":"https://github.com/google-research/tapas","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"question-answering","task_name":"Question Answering"}],"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":"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":"mate","method_name":"MATE"},{"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":[{"slug":"mate","name":"MATE","full_name":"MATE"}],"results":[{"leaderboard":"/sota/question-answering-on-hybridqa","task":"Question Answering","dataset":"HybridQA","model":"MATE Ponter","rank_in_archive_order":2,"of":4,"metrics":{"ANS-EM":"62.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.04312","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}