Toward a better understanding of causality between verbal events: Extraction and analysis of the causal power of verb-verb associations

Mehwish Riaz, Roxana Girju

Research output: Contribution to conferencePaper

Abstract

The identification of causal relations between verbal events is important for achieving natural language understanding. However, the problem has proven notoriously difficult since it is not clear which types of knowledge are necessary to solve this challenging problem close to human level performance. Instead of employing a large set of features proved useful in other NLP tasks, we split the problem in smaller sub problems. Since verbs play a very important role in causal relations, in this paper we harness, explore, and evaluate the predictive power of causal associations of verb-verb pairs. More specifically, we propose a set of knowledge-rich metrics to learn the likelihood of causal relations between verbs. Employing these metrics, we automatically generate a knowledge base (KBc) which identifies three categories of verb pairs: Strongly Causal, Ambiguous, and Strongly Non-causal. The knowledge base is evaluated empirically. The results show that our metrics perform significantly better than the state-of-the-art on the task of detecting causal verbal events.

Original languageEnglish (US)
StatePublished - Aug 2013
Event14th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2013 - Metz, France
Duration: Aug 22 2013Aug 24 2013

Other

Other14th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2013
CountryFrance
CityMetz
Period8/22/138/24/13

Fingerprint

Causality
Metric
Knowledge Base
Ambiguous
Large Set
Natural Language
Likelihood
Necessary
Evaluate
Knowledge

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Modeling and Simulation
  • Human-Computer Interaction

Cite this

Riaz, M., & Girju, R. (2013). Toward a better understanding of causality between verbal events: Extraction and analysis of the causal power of verb-verb associations. Paper presented at 14th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2013, Metz, France.

Toward a better understanding of causality between verbal events : Extraction and analysis of the causal power of verb-verb associations. / Riaz, Mehwish; Girju, Roxana.

2013. Paper presented at 14th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2013, Metz, France.

Research output: Contribution to conferencePaper

Riaz, M & Girju, R 2013, 'Toward a better understanding of causality between verbal events: Extraction and analysis of the causal power of verb-verb associations', Paper presented at 14th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2013, Metz, France, 8/22/13 - 8/24/13.
Riaz M, Girju R. Toward a better understanding of causality between verbal events: Extraction and analysis of the causal power of verb-verb associations. 2013. Paper presented at 14th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2013, Metz, France.
Riaz, Mehwish ; Girju, Roxana. / Toward a better understanding of causality between verbal events : Extraction and analysis of the causal power of verb-verb associations. Paper presented at 14th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2013, Metz, France.
@conference{9dc0802bf305494b8b0d95d54194cf9e,
title = "Toward a better understanding of causality between verbal events: Extraction and analysis of the causal power of verb-verb associations",
abstract = "The identification of causal relations between verbal events is important for achieving natural language understanding. However, the problem has proven notoriously difficult since it is not clear which types of knowledge are necessary to solve this challenging problem close to human level performance. Instead of employing a large set of features proved useful in other NLP tasks, we split the problem in smaller sub problems. Since verbs play a very important role in causal relations, in this paper we harness, explore, and evaluate the predictive power of causal associations of verb-verb pairs. More specifically, we propose a set of knowledge-rich metrics to learn the likelihood of causal relations between verbs. Employing these metrics, we automatically generate a knowledge base (KBc) which identifies three categories of verb pairs: Strongly Causal, Ambiguous, and Strongly Non-causal. The knowledge base is evaluated empirically. The results show that our metrics perform significantly better than the state-of-the-art on the task of detecting causal verbal events.",
author = "Mehwish Riaz and Roxana Girju",
year = "2013",
month = "8",
language = "English (US)",
note = "14th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2013 ; Conference date: 22-08-2013 Through 24-08-2013",

}

TY - CONF

T1 - Toward a better understanding of causality between verbal events

T2 - Extraction and analysis of the causal power of verb-verb associations

AU - Riaz, Mehwish

AU - Girju, Roxana

PY - 2013/8

Y1 - 2013/8

N2 - The identification of causal relations between verbal events is important for achieving natural language understanding. However, the problem has proven notoriously difficult since it is not clear which types of knowledge are necessary to solve this challenging problem close to human level performance. Instead of employing a large set of features proved useful in other NLP tasks, we split the problem in smaller sub problems. Since verbs play a very important role in causal relations, in this paper we harness, explore, and evaluate the predictive power of causal associations of verb-verb pairs. More specifically, we propose a set of knowledge-rich metrics to learn the likelihood of causal relations between verbs. Employing these metrics, we automatically generate a knowledge base (KBc) which identifies three categories of verb pairs: Strongly Causal, Ambiguous, and Strongly Non-causal. The knowledge base is evaluated empirically. The results show that our metrics perform significantly better than the state-of-the-art on the task of detecting causal verbal events.

AB - The identification of causal relations between verbal events is important for achieving natural language understanding. However, the problem has proven notoriously difficult since it is not clear which types of knowledge are necessary to solve this challenging problem close to human level performance. Instead of employing a large set of features proved useful in other NLP tasks, we split the problem in smaller sub problems. Since verbs play a very important role in causal relations, in this paper we harness, explore, and evaluate the predictive power of causal associations of verb-verb pairs. More specifically, we propose a set of knowledge-rich metrics to learn the likelihood of causal relations between verbs. Employing these metrics, we automatically generate a knowledge base (KBc) which identifies three categories of verb pairs: Strongly Causal, Ambiguous, and Strongly Non-causal. The knowledge base is evaluated empirically. The results show that our metrics perform significantly better than the state-of-the-art on the task of detecting causal verbal events.

UR - http://www.scopus.com/inward/record.url?scp=84987924224&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84987924224&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84987924224

ER -