Back to Search Start Over

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

Authors :
Gu, Yuling
Fu, Yao
Pyatkin, Valentina
Magnusson, Ian
Mishra, Bhavana Dalvi
Clark, Peter
Publication Year :
2022

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).<br />Comment: Accepted at The Third Workshop on Figurative Language Processing @ EMNLP 2022

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2210.16407
Document Type :
Working Paper