Semantic Frame Induction with Deep Metric Learning
This work addresses the challenge of improving semantic frame induction for natural language processing tasks, but it is incremental as it builds on existing methods with supervised fine-tuning.
The paper tackles the problem of semantic frame induction by proposing a supervised approach that fine-tunes contextualized embeddings using deep metric learning, resulting in improvements of about 8 points or more in clustering evaluation scores on FrameNet.
Recent studies have demonstrated the usefulness of contextualized word embeddings in unsupervised semantic frame induction. However, they have also revealed that generic contextualized embeddings are not always consistent with human intuitions about semantic frames, which causes unsatisfactory performance for frame induction based on contextualized embeddings. In this paper, we address supervised semantic frame induction, which assumes the existence of frame-annotated data for a subset of predicates in a corpus and aims to build a frame induction model that leverages the annotated data. We propose a model that uses deep metric learning to fine-tune a contextualized embedding model, and we apply the fine-tuned contextualized embeddings to perform semantic frame induction. Our experiments on FrameNet show that fine-tuning with deep metric learning considerably improves the clustering evaluation scores, namely, the B-cubed F-score and Purity F-score, by about 8 points or more. We also demonstrate that our approach is effective even when the number of training instances is small.