{"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/turl-table-understanding-through","title":"TURL: Table Understanding through Representation Learning","arxiv_id":"2006.14806","date":"2020-06-26","proceeding":null,"authors":["Xiang Deng","Huan Sun","Alyssa Lees","You Wu","Cong Yu"],"abstract":"Relational tables on the Web store a vast amount of knowledge. Owing to the wealth of such tables, there has been tremendous progress on a variety of tasks in the area of table understanding. However, existing work generally relies on heavily-engineered task-specific features and model architectures. In this paper, we present TURL, a novel framework that introduces the pre-training/fine-tuning paradigm to relational Web tables. During pre-training, our framework learns deep contextualized representations on relational tables in an unsupervised manner. Its universal model design with pre-trained representations can be applied to a wide range of tasks with minimal task-specific fine-tuning. Specifically, we propose a structure-aware Transformer encoder to model the row-column structure of relational tables, and present a new Masked Entity Recovery (MER) objective for pre-training to capture the semantics and knowledge in large-scale unlabeled data. We systematically evaluate TURL with a benchmark consisting of 6 different tasks for table understanding (e.g., relation extraction, cell filling). We show that TURL generalizes well to all tasks and substantially outperforms existing methods in almost all instances.","url_abs":"https://arxiv.org/abs/2006.14806v2","url_pdf":"https://arxiv.org/pdf/2006.14806v2.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":"turl-table-understanding-through","repo_url":"https://github.com/sunlab-osu/TURL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cell-entity-annotation","task_name":"Cell Entity Annotation"},{"task_slug":"column-type-annotation","task_name":"Column Type Annotation"},{"task_slug":"columns-property-annotation","task_name":"Columns Property Annotation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"table-annotation","task_name":"Table annotation"}],"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":"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":"turl","method_name":"TURL"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[{"slug":"wikitables-turl","name":"WikiTables-TURL","full_name":""}],"methods_introduced":[{"slug":"turl","name":"TURL","full_name":"TURL: Table Understanding through Representation Learning"}],"results":[{"leaderboard":"/sota/cell-entity-annotation-on-wikitables-turl-cea","task":"Cell Entity Annotation","dataset":"WikiTables-TURL-CEA","model":"TURL","rank_in_archive_order":1,"of":1,"metrics":{"F1 (%)":"68"},"uses_additional_data":false},{"leaderboard":"/sota/cell-entity-annotation-on-wikipediags","task":"Cell Entity Annotation","dataset":"WikipediaGS","model":"TURL","rank_in_archive_order":1,"of":1,"metrics":{"F1 (%)":"67"},"uses_additional_data":false},{"leaderboard":"/sota/column-type-annotation-on-t2dv2","task":"Column Type Annotation","dataset":"T2Dv2","model":"TURL","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy (%)":"96.2"},"uses_additional_data":false},{"leaderboard":"/sota/column-type-annotation-on-wikitables-turl-cta","task":"Column Type Annotation","dataset":"WikiTables-TURL-CTA","model":"TURL","rank_in_archive_order":1,"of":3,"metrics":{"F1 (%)":"94.75"},"uses_additional_data":false},{"leaderboard":"/sota/column-type-annotation-on-wikipediags-cta","task":"Column Type Annotation","dataset":"WikipediaGS-CTA","model":"TURL","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy (%)":"74.6"},"uses_additional_data":false},{"leaderboard":"/sota/columns-property-annotation-on-wikitables","task":"Columns Property Annotation","dataset":"WikiTables-TURL-CPA","model":"TURL","rank_in_archive_order":1,"of":3,"metrics":{"F1 (%)":"94.91"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.14806","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.14806"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sunlab-osu/TURL","reach":null}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"9ad8fa09f0972efd","entry":"evaluate","repo":"sunlab-osu/TURL","repo_kind":"official","path":"run_BERT_RE_finetuning.py","file_url":"https://github.com/sunlab-osu/TURL/blob/HEAD/run_BERT_RE_finetuning.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9ad8fa09f0972efd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}