Semantic Frame Induction with Deep Metric Learning
Semantic Frame Induction with Deep Metric Learning
复制标题
DOI：
10.48550/arxiv.2304.14286
复制
发表时间：
2023-04
期刊：
影响因子：
--
通讯作者：
Kosuke Yamada;Ryohei Sasano;Koichi Takeda
中科院分区：
文献类型：
--
作者：
Kosuke Yamada;Ryohei Sasano;Koichi Takeda
最近的研究证明了语境化单词嵌入在无监督语义框架诱导中的作用。然而，他们也揭示了一般的语境化嵌入并不总是与人类关于语义框架的直觉一致，这导致了基于语境化嵌入的框架归纳的性能不佳。在本文中，我们讨论了有监督的语义框架归纳，它假设语料库中的谓词子集存在框架标注的数据，旨在建立一个利用标注数据的框架归纳模型。我们提出了一种使用深度度量学习来微调语境化嵌入模型的模型，并将微调后的语境化嵌入应用于语义框架归纳。我们在FrameNet上的实验表明，采用深度度量学习的微调显著提高了聚类评估分数，即B立方体F分数和纯净F分数，提高了约8分或更多。我们还证明了我们的方法即使在训练实例数量很少的情况下也是有效的。
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.