Skip to main navigation Skip to search Skip to main content

OPERA: Operation-Pivoted Discrete Reasoning over Text

  • Yongwei Zhou
  • , Junwei Bao*
  • , Chaoqun Duan
  • , Haipeng Sun
  • , Jiahui Liang
  • , Yifan Wang
  • , Jing Zhao
  • , Youzheng Wu
  • , Xiaodong He
  • , Tiejun Zhao
  • *Corresponding author for this work
  • Harbin Institute of Technology
  • JD AI Research

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

Abstract

Machine reading comprehension (MRC) that requires discrete reasoning involving symbolic operations, e.g., addition, sorting, and counting, is a challenging task. According to this nature, semantic parsing-based methods predict interpretable but complex logical forms. However, logical form generation is nontrivial and even a little perturbation in a logical form will lead to wrong answers. To alleviate this issue, multi-predictor -based methods are proposed to directly predict different types of answers and achieve improvements. However, they ignore the utilization of symbolic operations and encounter a lack of reasoning ability and interpretability. To inherit the advantages of these two types of methods, we propose OPERA, an operation-pivoted discrete reasoning framework, where lightweight symbolic operations (compared with logical forms) as neural modules are utilized to facilitate the reasoning ability and interpretability. Specifically, operations are first selected and then softly executed to simulate the answer reasoning procedure. Extensive experiments on both DROP and RACENum datasets show the reasoning ability of OPERA. Moreover, further analysis verifies its interpretability.

Original languageEnglish
Title of host publicationNAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics
Subtitle of host publicationHuman Language Technologies, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages1655-1666
Number of pages12
ISBN (Electronic)9781955917711
DOIs
StatePublished - 2022
Event2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022 - Hybrid, Seattle, United States
Duration: 10 Jul 202215 Jul 2022

Publication series

NameNAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

Conference

Conference2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022
Country/TerritoryUnited States
CityHybrid, Seattle
Period10/07/2215/07/22

Fingerprint

Dive into the research topics of 'OPERA: Operation-Pivoted Discrete Reasoning over Text'. Together they form a unique fingerprint.

Cite this