TY - GEN
T1 - Constructing a dictionary describing feature changes of arguments in event sentences
AU - Nakamura, Tetsuaki
AU - Kawahara, Daisuke
N1 - Publisher Copyright:
© 2016 Association for Computational Linguistics.
PY - 2016
Y1 - 2016
N2 - Common sense knowledge plays an essential role for natural language understanding, human-machine communication and so forth. In this paper, we acquire knowledge of events as common sense knowledge because there is a possibility that dictionaries of such knowledge are useful for recognition of implication relations in texts, inference of human activities and their planning, and so on. As for event knowledge, we focus on feature changes of arguments (hereafter, FCAs) in event sentences as knowledge of events. To construct a dictionary of FCAs, we propose a framework for acquiring such knowledge based on both of the automatic approach and the collective intelligence approach to exploit merits of both approaches. We acquired FCAs in event sentences through crowdsourcing and conducted the subjective evaluation to validate whether the FCAs are adequately acquired. As a result of the evaluation, it was shown that we were able to reasonably well capture FCAs in event sentences.
AB - Common sense knowledge plays an essential role for natural language understanding, human-machine communication and so forth. In this paper, we acquire knowledge of events as common sense knowledge because there is a possibility that dictionaries of such knowledge are useful for recognition of implication relations in texts, inference of human activities and their planning, and so on. As for event knowledge, we focus on feature changes of arguments (hereafter, FCAs) in event sentences as knowledge of events. To construct a dictionary of FCAs, we propose a framework for acquiring such knowledge based on both of the automatic approach and the collective intelligence approach to exploit merits of both approaches. We acquired FCAs in event sentences through crowdsourcing and conducted the subjective evaluation to validate whether the FCAs are adequately acquired. As a result of the evaluation, it was shown that we were able to reasonably well capture FCAs in event sentences.
UR - http://www.scopus.com/inward/record.url?scp=85059892298&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85059892298&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85059892298
T3 - Proceedings of the 4th Workshop on Events: Definition, Detection, Coreference, and Representation, EVENTS 2016 at the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2016
SP - 46
EP - 50
BT - Proceedings of the 4th Workshop on Events
A2 - Palmer, Martha
A2 - Hovy, Eduard
A2 - Mitamura, Teruko
A2 - O�Gorman, Tim
PB - Association for Computational Linguistics (ACL)
T2 - 4th Workshop on Events: Definition, Detection, Coreference, and Representation, EVENTS 2016 at the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2016
Y2 - 17 June 2016
ER -