Discrete Reasoning Templates for Natural Language Understanding

Hadeel Al-Negheimish, Pranava Madhyastha, Alessandra Russo

Student Research Workshop Long paper Paper

Gather-2F: Apr 22, Gather-2F: Apr 22 (13:00-15:00 UTC) [Join Gather Meeting]

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.

Connected Papers in EACL2021

Similar Papers