Hierarchical Relation-Guided Type-Sentence Alignment for Long-Tail Relation Extraction with Distant Supervision

Yang Li, Guodong Long, Tao Shen, Jing Jiang


Abstract
Distant supervision uses triple facts in knowledge graphs to label a corpus for relation extraction, leading to wrong labeling and long-tail problems. Some works use the hierarchy of relations for knowledge transfer to long-tail relations. However, a coarse-grained relation often implies only an attribute (e.g., domain or topic) of the distant fact, making it hard to discriminate relations based solely on sentence semantics. One solution is resorting to entity types, but open questions remain about how to fully leverage the information of entity types and how to align multi-granular entity types with sentences. In this work, we propose a novel model to enrich distantly-supervised sentences with entity types. It consists of (1) a pairwise type-enriched sentence encoding module injecting both context-free and -related backgrounds to alleviate sentence-level wrong labeling, and (2) a hierarchical type-sentence alignment module enriching a sentence with the triple fact’s basic attributes to support long-tail relations. Our model achieves new state-of-the-art results in overall and long-tail performance on benchmarks.
Anthology ID:
2022.findings-naacl.24
Volume:
Findings of the Association for Computational Linguistics: NAACL 2022
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
316–326
Language:
URL:
https://aclanthology.org/2022.findings-naacl.24
DOI:
10.18653/v1/2022.findings-naacl.24
Bibkey:
Cite (ACL):
Yang Li, Guodong Long, Tao Shen, and Jing Jiang. 2022. Hierarchical Relation-Guided Type-Sentence Alignment for Long-Tail Relation Extraction with Distant Supervision. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 316–326, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Hierarchical Relation-Guided Type-Sentence Alignment for Long-Tail Relation Extraction with Distant Supervision (Li et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-naacl.24.pdf
Video:
 https://aclanthology.org/2022.findings-naacl.24.mp4