Skip to main navigation Skip to search Skip to main content

Using Commonsense Knowledge to Answer Why-Questions

  • Stony Brook University
  • Allen Institute for AI
  • United States Naval Academy
  • University of Texas at Austin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

14 Scopus citations

Abstract

Answering questions in narratives about why events happened often requires commonsense knowledge external to the text. What aspects of this knowledge are available in large language models? What aspects can be made accessible via external commonsense resources? We study these questions in the context of answering questions in the TELLMEWHY dataset using COMET as a source of relevant commonsense relations. We analyze the effects of model size (T5 variants and GPT-3) along with methods of injecting knowledge (COMET) into these models. Results show that the largest models, as expected, yield substantial improvements over base models and injecting external knowledge helps models of all sizes. We also find that the format in which knowledge is provided is critical, and that smaller models benefit more from larger amounts of knowledge. Finally, we develop an ontology of knowledge types and analyze the relative coverage of the models across these categories.

Original languageEnglish
Title of host publicationProceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
EditorsYoav Goldberg, Zornitsa Kozareva, Yue Zhang
PublisherAssociation for Computational Linguistics (ACL)
Pages1204-1219
Number of pages16
ISBN (Electronic)9781959429401
DOIs
StatePublished - 2022
Event2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022 - Hybrid, Abu Dhabi, United Arab Emirates
Duration: Dec 7 2022Dec 11 2022

Publication series

NameProceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

Conference

Conference2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
Country/TerritoryUnited Arab Emirates
CityHybrid, Abu Dhabi
Period12/7/2212/11/22

Fingerprint

Dive into the research topics of 'Using Commonsense Knowledge to Answer Why-Questions'. Together they form a unique fingerprint.

Cite this