Commonsense causal reasoning between short texts

Zhiyi Luo, Yuchen Sha, Kenny Q. Zhu, Seung Won Hwang, Zhongyuan Wang

Research output: Contribution to conferencePaperpeer-review

22 Citations (Scopus)


Commonsense causal reasoning is the process of capturing and understanding the causal dependencies amongst events and actions. Such events and actions can be expressed in terms, phrases or sentences in natural language text. Therefore, one possible way of obtaining causal knowledge is by extracting causal relations between terms or phrases from a large text corpus. However, causal relations in text are sparse, ambiguous, and sometimes implicit, and thus difficult to obtain. This paper attacks the problem of commonsense causality reasoning between short texts (phrases and sentences) using a data driven approach. We propose a framework that automatically harvests a network of causal-effect terms from a large web corpus. Backed by this network, we propose a novel and effective metric to properly model the causality strength between terms. We show these signals can be aggregated for causality reasonings between short texts, including sentences and phrases. In particular, our approach outperforms all previously reported results in the standard SEMEVAL COPA task by substantial margins.

Original languageEnglish
Number of pages10
Publication statusPublished - 2016
Event15th International Conference on Principles of Knowledge Representation and Reasoning, KR 2016 - Cape Town, South Africa
Duration: 2016 Apr 252016 Apr 29


Other15th International Conference on Principles of Knowledge Representation and Reasoning, KR 2016
Country/TerritorySouth Africa
CityCape Town

Bibliographical note

Funding Information:
This work was partially supported by 2014 NSFC-NRF joint research scheme "Multi-lingual, Cross-cultural Semantic Association Network", international cooperation program managed by NRF of Korea (2014K2A2A2000519), and NSFC grant No. 61373031.

Publisher Copyright:
Copyright © 2016, Association for the Advancement of Artificial Intelligence ( All rights reserved.

All Science Journal Classification (ASJC) codes

  • Logic
  • Software


Dive into the research topics of 'Commonsense causal reasoning between short texts'. Together they form a unique fingerprint.

Cite this