Deriving Verb Predicates By Clustering Verbs with Arguments
This work addresses the need for more comprehensive verb clustering in natural language processing, particularly for applications like social media analysis, but it is incremental as it builds on existing methods like VerbKB.
The paper tackles the problem of limited coverage in hand-built verb clusters by automatically inducing verb clusters from corpus data using a novel low-dimensional embedding of verbs and their arguments, resulting in clusters that outperform hand-built ones in predicting sarcasm, sentiment, and locus of control in tweets.
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 low-dimensional 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.