Discrete Reasoning Templates for Natural Language Understanding
Computation and Language
2021-04-07 v1 Artificial Intelligence
Abstract
Reasoning about information from multiple parts of a passage to derive an answer is an open challenge for reading-comprehension models. In this paper, we present an approach that reasons about complex questions by decomposing them to simpler subquestions that can take advantage of single-span extraction reading-comprehension models, and derives the final answer according to instructions in a predefined reasoning template. We focus on subtraction-based arithmetic questions and evaluate our approach on a subset of the DROP dataset. We show that our approach is competitive with the state-of-the-art while being interpretable and requires little supervision
Cite
@article{arxiv.2104.02115,
title = {Discrete Reasoning Templates for Natural Language Understanding},
author = {Hadeel Al-Negheimish and Pranava Madhyastha and Alessandra Russo},
journal= {arXiv preprint arXiv:2104.02115},
year = {2021}
}
Comments
Published at EACL 2021 SRW