MatchPrompt: Prompt-based Open Relation Extraction with Semantic Consistency Guided Clustering
Jiaxin Wang, Lingling Zhang, Jun Liu, Xi Liang, Yujie Zhong, Yaqiang Wu
Abstract
Relation clustering is a general approach for open relation extraction (OpenRE). Current methods have two major problems. One is that their good performance relies on large amounts of labeled and pre-defined relational instances for pre-training, which are costly to acquire in reality. The other is that they only focus on learning a high-dimensional metric space to measure the similarity of novel relations and ignore the specific relational representations of clusters. In this work, we propose a new prompt-based framework named MatchPrompt, which can realize OpenRE with efficient knowledge transfer from only a few pre-defined relational instances as well as mine the specific meanings for cluster interpretability. To our best knowledge, we are the first to introduce a prompt-based framework for unlabeled clustering. Experimental results on different datasets show that MatchPrompt achieves the new SOTA results for OpenRE.
BibTeX
@inproceedings{wang-etal-2022-matchprompt,
title = "{M}atch{P}rompt: Prompt-based Open Relation Extraction with Semantic Consistency Guided Clustering",
author = "Wang, Jiaxin and
Zhang, Lingling and
Liu, Jun and
Liang, Xi and
Zhong, Yujie and
Wu, Yaqiang",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.537/",
doi = "10.18653/v1/2022.emnlp-main.537",
pages = "7875--7888"
}