Just-DREAM-about-it: Figurative Language Understanding with DREAM-FLUTE

5Citations
Citations of this article
26Readers
Mendeley users who have this article in their library.

Abstract

Figurative language (e.g., “he flew like the wind”) is challenging to understand, as it is hard to tell what implicit information is being conveyed from the surface form alone. We hypothesize that to perform this task well, the reader needs to mentally elaborate the scene being described to identify a sensible meaning of the language. We present DREAM-FLUTE, a figurative language understanding system that does this, first forming a “mental model” of situations described in a premise and hypothesis before making an entailment/contradiction decision and generating an explanation. DREAM-FLUTE uses an existing scene elaboration model, DREAM, for constructing its “mental model.” In the FigLang2022 Shared Task evaluation, DREAM-FLUTE achieved (joint) first place (Acc@60=63.3%), and can perform even better with ensemble techniques, demonstrating the effectiveness of this approach. More generally, this work suggests that adding a reflective component to pretrained language models can improve their performance beyond standard fine-tuning (3.3% improvement in Acc@60).

Cite

CITATION STYLE

APA

Gu, Y., Fu, Y., Pyatkin, V., Magnusson, I., Mishra, B. D., & Clark, P. (2022). Just-DREAM-about-it: Figurative Language Understanding with DREAM-FLUTE. In FLP 2022 - 3rd Workshop on Figurative Language Processing, Proceedings of the Workshop (pp. 84–93). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2022.flp-1.12

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free