Deriving Verb Predicates By Clustering Verbs with Arguments

TL;DR

This paper introduces a novel method for automatically clustering verbs with their argument types using low-dimensional embeddings, improving the prediction of sarcasm, sentiment, and locus of control in tweets compared to hand-crafted clusters.

Contribution

It presents a new approach to cluster verbs with arguments from VerbKB using embeddings, enabling argument-dependent clustering and better predictive performance.

Findings

Clusters outperform hand-built classes in sarcasm prediction

Method adapts to specific corpora like Twitter

Verb clusters improve sentiment and control prediction

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 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.