TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Text-To-SQL	spider	MAPO + TABERTLarge (K = 3)	Exact Match Accuracy (Dev)	64.5	# 10
Semantic Parsing	WikiTableQuestions	MAPO + TABERTLarge (K = 3)	Accuracy (Dev)	52.2	# 7
Semantic Parsing	WikiTableQuestions	MAPO + TABERTLarge (K = 3)	Accuracy (Test)	51.8	# 10

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/tabert-pretraining-for-joint-understanding-of/text-to-sql-on-spider)](https://paperswithcode.com/sota/text-to-sql-on-spider?p=tabert-pretraining-for-joint-understanding-of)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/tabert-pretraining-for-joint-understanding-of/semantic-parsing-on-wikitablequestions)](https://paperswithcode.com/sota/semantic-parsing-on-wikitablequestions?p=tabert-pretraining-for-joint-understanding-of)`

TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data

ACL 2020 · Pengcheng Yin, Graham Neubig, Wen-tau Yih, Sebastian Riedel ·

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 .

PDF Abstract ACL 2020 PDF ACL 2020 Abstract

Code

Add Remove Mark official

facebookresearch/tabert official

578

Tasks

Add Remove

Semantic Parsing

Text-To-SQL

Datasets

SPIDER

Spider Spider-Realistic

WikiTableQuestions

Results from the Paper

Add Remove

Ranked #10 on Text-To-SQL on spider (Exact Match Accuracy (Dev) metric)

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Text-To-SQL	spider	MAPO + TABERTLarge (K = 3)	Exact Match Accuracy (Dev)	64.5	# 10	Compare
Semantic Parsing	WikiTableQuestions	MAPO + TABERTLarge (K = 3)	Accuracy (Dev)	52.2	# 7	Compare
Semantic Parsing	WikiTableQuestions	MAPO + TABERTLarge (K = 3)	Accuracy (Test)	51.8	# 10	Compare

Methods

Add Remove

Adam • Attention Dropout • BERT • Dense Connections • Dropout • GELU • Gradient Clipping • Layer Normalization • Linear Layer • Linear Warmup With Linear Decay • Multi-Head Attention • Residual Connection • Scaled Dot-Product Attention • Softmax • TaBERT • Weight Decay • WordPiece

Edit Social Preview

TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit Add Remove

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Add Remove

Methods

Add Remove