Open Hierarchical Relation Extraction
Kai Zhang, Yuan Yao, Ruobing Xie, Xu Han, Zhiyuan Liu, Fen Lin, Leyu Lin, Maosong Sun
Abstract
Open relation extraction (OpenRE) aims to extract novel relation types from open-domain corpora, which plays an important role in completing the relation schemes of knowledge bases (KBs). Most OpenRE methods cast different relation types in isolation without considering their hierarchical dependency. We argue that OpenRE is inherently in close connection with relation hierarchies. To establish the bidirectional connections between OpenRE and relation hierarchy, we propose the task of open hierarchical relation extraction and present a novel OHRE framework for the task. We propose a dynamic hierarchical triplet objective and hierarchical curriculum training paradigm, to effectively integrate hierarchy information into relation representations for better novel relation extraction. We also present a top-down hierarchy expansion algorithm to add the extracted relations into existing hierarchies with reasonable interpretability. Comprehensive experiments show that OHRE outperforms state-of-the-art models by a large margin on both relation clustering and hierarchy expansion.
BibTeX
@inproceedings{zhang-etal-2021-open,
title = "Open Hierarchical Relation Extraction",
author = "Zhang, Kai and
Yao, Yuan and
Xie, Ruobing and
Han, Xu and
Liu, Zhiyuan and
Lin, Fen and
Lin, Leyu and
Sun, Maosong",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.452/",
doi = "10.18653/v1/2021.naacl-main.452",
pages = "5682--5693"
}