Verb Pattern: A Probabilistic Semantic Representation on Verbs
This work addresses a specific bottleneck in natural language processing for tasks requiring detailed semantic understanding, though it appears incremental in scope.
The paper tackles the problem of representing verb semantics by introducing verb patterns as a finer-grained alternative to traditional role-based representations, achieving high effectiveness in experiments.
Verbs are important in semantic understanding of natural language. Traditional verb representations, such as FrameNet, PropBank, VerbNet, focus on verbs' roles. These roles are too coarse to represent verbs' semantics. In this paper, we introduce verb patterns to represent verbs' semantics, such that each pattern corresponds to a single semantic of the verb. First we analyze the principles for verb patterns: generality and specificity. Then we propose a nonparametric model based on description length. Experimental results prove the high effectiveness of verb patterns. We further apply verb patterns to context-aware conceptualization, to show that verb patterns are helpful in semantic-related tasks.