TAble PArSing
Year: 2,020
Journal: Association for Computational Linguistics
Languages: English
Programming languages: Python
Input data:
text
Project website: https://github.com/google-research/tapas
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.