# Acquiring Frame Element Knowledge with Deep Metric Learning for Semantic Frame Induction

arXiv: https://arxiv.org/abs/2305.13944 · HTML: https://mlsanity.com/paper/2305.13944/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 23 May 2023.

## Builds on (most cited first, 8 of 8)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [A Metric Learning Reality Check](https://mlsanity.com/paper/2003.08505/) (2020)
- [AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations](https://mlsanity.com/paper/1905.00292/) (2019)
- [Semantic Frame Induction using Masked Word Embeddings and Two-Step Clustering](https://mlsanity.com/paper/2105.13466/) (2021)
- [HHMM at SemEval-2019 Task 2: Unsupervised Frame Induction using Contextualized Word Embeddings](https://mlsanity.com/paper/1905.01739/) (2019)
- [Semantic Frame Induction with Deep Metric Learning](https://mlsanity.com/paper/2304.14286/) (2023)

## Abstract (arXiv)

The semantic frame induction tasks are defined as a clustering of words into the frames that they evoke, and a clustering of their arguments according to the frame element roles that they should fill. In this paper, we address the latter task of argument clustering, which aims to acquire frame element knowledge, and propose a method that applies deep metric learning. In this method, a pre-trained language model is fine-tuned to be suitable for distinguishing frame element roles through the use of frame-annotated data, and argument clustering is performed with embeddings obtained from the fine-tuned model. Experimental results on FrameNet demonstrate that our method achieves substantially better performance than existing methods.