TAble PArSing

Year: 2,020
Journal: Association for Computational Linguistics
Languages: English
Programming languages: Python
Input data:

text

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.

Sign In

Register

Reset Password

Please enter your username or email address, you will receive a link to create a new password via email.