Can I read CURIE: An Iterative Querying Approach for Reasoning About Situations on EtoBox?

CURIE: An Iterative Querying Approach for Reasoning About Situations by Rajagopal, Dheeraj; Madaan, Aman; Tandon, Niket; Yang, Yiming; Prabhumoye, Shrimai; Ravichander, Abhilasha; Clark, Peter; Hovy, Eduard is a scholarly article available to read on EtoBox.

What is CURIE: An Iterative Querying Approach for Reasoning About Situations about?

Recently, models have been shown to predict the effects of unexpected situations, e.g., would cloudy skies help or hinder plant growth? Given a context, the goal of such situational reasoning is to elicit the consequences of a new situation (st) that arises in that context. We propose a method to iteratively build a graph of relevant consequences explicitly in a structured situational graph (st-graph) using natural language queries over a finetuned language model (M). Across multiple domains, CURIE generates st-graphs that humans find relevant and meaningful in eliciting the consequences of a new situation. We show that st-graphs generated by CURIE improve a situational reasoning end task (WIQA-QA) by 3 points on accuracy by simply augmenting their input with our generated situational graphs, especially for a hard subset that requires background knowledge and multi-hop reasoning.

Author

Rajagopal, Dheeraj; Madaan, Aman; Tandon, Niket; Yang, Yiming; Prabhumoye, Shrimai; Ravichander, Abhilasha; Clark, Peter; Hovy, Eduard

Published

2021

Language

EN