TAPAS: Weakly Supervised Table Parsing via Pre-training

by   Jonathan Herzig, et al.

Answering natural language questions over tables is usually seen as a semantic parsing task. To alleviate the collection cost of full logical forms, one popular approach focuses on weak supervision consisting of denotations instead of logical forms. However, training semantic parsers from weak supervision poses difficulties, and in addition, the generated logical forms are only used as an intermediate step prior to retrieving the denotation. In this paper, we present TAPAS, an approach to question answering over tables without generating logical forms. TAPAS trains from weak supervision, and predicts the denotation by selecting table cells and optionally applying a corresponding aggregation operator to such selection. TAPAS extends BERT's architecture to encode tables as input, initializes from an effective joint pre-training of text segments and tables crawled from Wikipedia, and is trained end-to-end. We experiment with three different semantic parsing datasets, and find that TAPAS outperforms or rivals semantic parsing models by improving state-of-the-art accuracy on SQA from 55.1 to 67.2 and performing on par with the state-of-the-art on WIKISQL and WIKITQ, but with a simpler model architecture. We additionally find that transfer learning, which is trivial in our setting, from WIKISQL to WIKITQ, yields 48.7 accuracy, 4.2 points above the state-of-the-art.


Effective Search of Logical Forms for Weakly Supervised Knowledge-Based Question Answering

Many algorithms for Knowledge-Based Question Answering (KBQA) depend on ...

Compositional Semantic Parsing on Semi-Structured Tables

Two important aspects of semantic parsing for question answering are the...

Generating Logical Forms from Graph Representations of Text and Entities

Structured information about entities is critical for many semantic pars...

Compositional pre-training for neural semantic parsing

Semantic parsing is the process of translating natural language utteranc...

Neural Multi-Step Reasoning for Question Answering on Semi-Structured Tables

Advances in natural language processing tasks have gained momentum in re...

Code-Style In-Context Learning for Knowledge-Based Question Answering

Current methods for Knowledge-Based Question Answering (KBQA) usually re...

TableParser: Automatic Table Parsing with Weak Supervision from Spreadsheets

Tables have been an ever-existing structure to store data. There exist n...

Code Repositories


Predictions on SQA

view repo

Please sign up or login with your details

Forgot password? Click here to reset