TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/TaBERT: Pretraining for Joint Understanding of Textual and...

TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data

Pengcheng Yin, Graham Neubig, Wen-tau Yih, Sebastian Riedel

2020-05-17ACL 2020 6Semantic ParsingText-To-SQLForm
PaperPDFCode(official)

Abstract

Recent years have witnessed the burgeoning of pretrained language models (LMs) for text-based natural language (NL) understanding tasks. Such models are typically trained on free-form NL text, hence may not be suitable for tasks like semantic parsing over structured data, which require reasoning over both free-form NL questions and structured tabular data (e.g., database tables). In this paper we present TaBERT, a pretrained LM that jointly learns representations for NL sentences and (semi-)structured tables. TaBERT is trained on a large corpus of 26 million tables and their English contexts. In experiments, neural semantic parsers using TaBERT as feature representation layers achieve new best results on the challenging weakly-supervised semantic parsing benchmark WikiTableQuestions, while performing competitively on the text-to-SQL dataset Spider. Implementation of the model will be available at http://fburl.com/TaBERT .

Results

TaskDatasetMetricValueModel
Semantic ParsingWikiTableQuestionsAccuracy (Dev)52.2MAPO + TABERTLarge (K = 3)
Semantic ParsingWikiTableQuestionsAccuracy (Test)51.8MAPO + TABERTLarge (K = 3)
Semantic ParsingspiderExact Match Accuracy (Dev)64.5MAPO + TABERTLarge (K = 3)
Text-To-SQLspiderExact Match Accuracy (Dev)64.5MAPO + TABERTLarge (K = 3)

Related Papers

FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation2025-07-11CogniSQL-R1-Zero: Lightweight Reinforced Reasoning for Efficient SQL Generation2025-07-08XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL2025-07-07Where, What, Why: Towards Explainable Driver Attention Prediction2025-06-29Controlled Retrieval-augmented Context Evaluation for Long-form RAG2025-06-24SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications2025-06-23FormGym: Doing Paperwork with Agents2025-06-17FreeQ-Graph: Free-form Querying with Semantic Consistent Scene Graph for 3D Scene Understanding2025-06-16