{"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/tabbie-pretrained-representations-of-tabular","title":"TABBIE: Pretrained Representations of Tabular Data","arxiv_id":"2105.02584","date":"2021-05-06","proceeding":"NAACL 2021 4","authors":["Hiroshi Iida","Dung Thai","Varun Manjunatha","Mohit Iyyer"],"abstract":"Existing work on tabular representation learning jointly models tables and associated text using self-supervised objective functions derived from pretrained language models such as BERT. While this joint pretraining improves tasks involving paired tables and text (e.g., answering questions about tables), we show that it underperforms on tasks that operate over tables without any associated text (e.g., populating missing cells). We devise a simple pretraining objective (corrupt cell detection) that learns exclusively from tabular data and reaches the state-of-the-art on a suite of table based prediction tasks. Unlike competing approaches, our model (TABBIE) provides embeddings of all table substructures (cells, rows, and columns), and it also requires far less compute to train. A qualitative analysis of our model's learned cell, column, and row representations shows that it understands complex table semantics and numerical trends.","url_abs":"https://arxiv.org/abs/2105.02584v1","url_pdf":"https://arxiv.org/pdf/2105.02584v1.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":"tabbie-pretrained-representations-of-tabular","repo_url":"https://github.com/SFIG611/tabbie","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"tabbie-pretrained-representations-of-tabular","repo_url":"https://github.com/awslabs/hypergraph-tabular-lm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cell-detection","task_name":"Cell Detection"},{"task_slug":"column-type-annotation","task_name":"Column Type Annotation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"table-annotation","task_name":"Table annotation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tabbie","method_name":"TABBIE"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[{"slug":"tabbie","name":"TABBIE","full_name":"TABBIE"}],"results":[{"leaderboard":"/sota/column-type-annotation-on-viznet-sato-full","task":"Column Type Annotation","dataset":"VizNet-Sato-Full","model":"TaBERT","rank_in_archive_order":4,"of":4,"metrics":{"Weighted-F1":"97.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.02584","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}