CIKQA: Learning Commonsense Inference with a Unified Knowledge-in-the-loop QA Paradigm

Hongming Zhang, Yintong Huo, Yanai Elazar, Yangqiu Song, Yoav Goldberg, Dan Roth

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

Abstract

We propose a new commonsense reasoning benchmark to motivate commonsense reasoning progress from two perspectives: (1) Evaluating whether models can distinguish knowledge quality by predicting if the knowledge is enough to answer the question; (2) Evaluating whether models can develop commonsense inference capabilities that generalize across tasks. We first extract supporting knowledge for each question and ask humans to annotate whether the auto-extracted knowledge is enough to answer the question or not. After that, we convert different tasks into a unified question-answering format to evaluate the models’ generalization capabilities. We name the benchmark Commonsense Inference with Knowledge-in-the-loop Question Answering (CIKQA). Experiments show that with our learning paradigm, models demonstrate encouraging generalization capabilities. At the same time, we also notice that distinguishing knowledge quality remains challenging for current commonsense reasoning models.

Original languageEnglish
Title of host publicationEACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Findings of EACL 2023
PublisherAssociation for Computational Linguistics (ACL)
Pages114-124
Number of pages11
ISBN (Electronic)9781959429470
StatePublished - 2023
Event17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 - Findings of EACL 2023 - Dubrovnik, Croatia
Duration: 2 May 20236 May 2023

Publication series

NameEACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Findings of EACL 2023

Conference

Conference17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 - Findings of EACL 2023
Country/TerritoryCroatia
CityDubrovnik
Period2/05/236/05/23

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Software
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'CIKQA: Learning Commonsense Inference with a Unified Knowledge-in-the-loop QA Paradigm'. Together they form a unique fingerprint.

Cite this