Semantic Frame Induction from a Real-World Corpus

Shogo Tsujimoto, Kosuke Yamada, Ryohei Sasano

Keywords: frame induction, frame semantics, FrameNet

TL;DR: We perform semantic frame induction from C4 to address limitations of FrameNet-based evaluation and propose an evaluation method that compares induced clusters with FrameNet examples to assess both alignment with existing frames and emerging usages.

Abstract:

Recent studies on semantic frame induction have demonstrated that the emergence of pre-trained language models (PLMs) has led to more accurate results.
However, most existing studies evaluate the performance using frame resources such as FrameNet, which may not accurately reflect real-world language usage.
In this study, we conduct semantic frame induction using the Colossal Clean Crawled Corpus (C4) and assess the applicability of existing frame induction methods to real-world data.
Our experimental results demonstrate that existing frame induction methods are effective on real-world data and that frames corresponding to novel concepts can be induced.

Archival Status: Archival

Paper Length: Short Paper (up to 4 pages of content)

Submission Number: 267