Fusion Makes Perfection: An Efficient Multi-Grained Matching Approach for Zero-Shot Relation Extraction
Shilong Li, Ge Bai, Zhang Zhang, Ying Liu, Chenji Lu, Daichi Guo, Ruifang Liu, Sun Yong
Abstract
Predicting unseen relations that cannot be observed during the training phase is a challenging task in relation extraction. Previous works have made progress by matching the semantics between input instances and label descriptions. However, fine-grained matching often requires laborious manual annotation, and rich interactions between instances and label descriptions come with significant computational overhead. In this work, we propose an efficient multi-grained matching approach that uses virtual entity matching to reduce manual annotation cost, and fuses coarse-grained recall and fine-grained classification for rich interactions with guaranteed inference speed.Experimental results show that our approach outperforms the previous State Of The Art (SOTA) methods, and achieves a balance between inference efficiency and prediction accuracy in zero-shot relation extraction tasks.Our code is available at https://github.com/longls777/EMMA.
BibTeX
@inproceedings{li-etal-2024-fusion,
title = "Fusion Makes Perfection: An Efficient Multi-Grained Matching Approach for Zero-Shot Relation Extraction",
author = "Li, Shilong and
Bai, Ge and
Zhang, Zhang and
Liu, Ying and
Lu, Chenji and
Guo, Daichi and
Liu, Ruifang and
Yong, Sun",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-short.7/",
doi = "10.18653/v1/2024.naacl-short.7",
pages = "79--85"
}