TY - GEN
T1 - A step-wise usage-based method for inducing polysemy-aware verb classes
AU - Kawahara, Daisuke
AU - Peterson, Daniel W.
AU - Palmer, Martha
N1 - Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2014
Y1 - 2014
N2 - We present an unsupervised method for inducing verb classes from verb uses in gigaword corpora. Our method consists of two clustering steps: verb-specific semantic frames are first induced by clustering verb uses in a corpus and then verb classes are induced by clustering these frames. By taking this step-wise approach, we can not only generate verb classes based on a massive amount of verb uses in a scalable manner, but also deal with verb polysemy, which is bypassed by most of the previous studies on verb clustering. In our experiments, we acquire semantic frames and verb classes from two giga-word corpora, the larger comprising 20 billion words. The effectiveness of our approach is verified through quantitative evaluations based on polysemy-aware gold-standard data.
AB - We present an unsupervised method for inducing verb classes from verb uses in gigaword corpora. Our method consists of two clustering steps: verb-specific semantic frames are first induced by clustering verb uses in a corpus and then verb classes are induced by clustering these frames. By taking this step-wise approach, we can not only generate verb classes based on a massive amount of verb uses in a scalable manner, but also deal with verb polysemy, which is bypassed by most of the previous studies on verb clustering. In our experiments, we acquire semantic frames and verb classes from two giga-word corpora, the larger comprising 20 billion words. The effectiveness of our approach is verified through quantitative evaluations based on polysemy-aware gold-standard data.
UR - http://www.scopus.com/inward/record.url?scp=84906929595&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84906929595&partnerID=8YFLogxK
U2 - 10.3115/v1/p14-1097
DO - 10.3115/v1/p14-1097
M3 - Conference contribution
AN - SCOPUS:84906929595
SN - 9781937284725
T3 - 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Proceedings of the Conference
SP - 1030
EP - 1040
BT - Long Papers
PB - Association for Computational Linguistics (ACL)
T2 - 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014
Y2 - 22 June 2014 through 27 June 2014
ER -