Verb Sense Clustering using Contextualized Word Representations for Semantic Frame Induction
This work addresses the problem of automating semantic frame induction for natural language processing, which is incremental as it applies existing contextualized representations to a known bottleneck in semantic analysis.
The paper investigated how well contextualized word representations, particularly BERT and its variants, can recognize and induce semantic frames for verbs in English using FrameNet and PropBank, showing they are considerably informative for this task.
Contextualized word representations have proven useful for various natural language processing tasks. However, it remains unclear to what extent these representations can cover hand-coded semantic information such as semantic frames, which specify the semantic role of the arguments associated with a predicate. In this paper, we focus on verbs that evoke different frames depending on the context, and we investigate how well contextualized word representations can recognize the difference of frames that the same verb evokes. We also explore which types of representation are suitable for semantic frame induction. In our experiments, we compare seven different contextualized word representations for two English frame-semantic resources, FrameNet and PropBank. We demonstrate that several contextualized word representations, especially BERT and its variants, are considerably informative for semantic frame induction. Furthermore, we examine the extent to which the contextualized representation of a verb can estimate the number of frames that the verb can evoke.