Deriving verb predicates by clustering verbs with arguments.

Files
1708.00416v1.pdf(386.51 KB)
First author draft
Date
2017
DOI
Authors
Sedoc, João
Wijaya, Derry
Rouhizadeh, Masoud
Schwartz, Andy
Ungar, Lyle H.
Version
First author draft
OA Version
Citation
João Sedoc, Derry Wijaya, Masoud Rouhizadeh, Andy Schwartz, Lyle H Ungar. 2017. "Deriving Verb Predicates By Clustering Verbs with Arguments.." CoRR, Volume abs/1708.00416.
Abstract
Hand-built verb clusters such as the widely used Levin classes (Levin, 1993) have proved useful, but have limited coverage. Verb classes automatically induced from corpus data such as those from VerbKB (Wijaya, 2016), on the other hand, can give clusters with much larger coverage, and can be adapted to specific corpora such as Twitter. We present a method for clustering the outputs of VerbKB: verbs with their multiple argument types, e.g.“marry(person, person)”, “feel(person, emotion).” We make use of a novel lowdimensional embedding of verbs and their arguments to produce high quality clusters in which the same verb can be in different clusters depending on its argument type. The resulting verb clusters do a better job than hand-built clusters of predicting sarcasm, sentiment, and locus of control in tweets.
Description
License