Leveraging 2-hop Distant Supervision from Table Entity Pairs for Relation Extraction

Xiang Deng, Huan Sun


Abstract
Distant supervision (DS) has been widely used to automatically construct (noisy) labeled data for relation extraction (RE). Given two entities, distant supervision exploits sentences that directly mention them for predicting their semantic relation. We refer to this strategy as 1-hop DS, which unfortunately may not work well for long-tail entities with few supporting sentences. In this paper, we introduce a new strategy named 2-hop DS to enhance distantly supervised RE, based on the observation that there exist a large number of relational tables on the Web which contain entity pairs that share common relations. We refer to such entity pairs as anchors for each other, and collect all sentences that mention the anchor entity pairs of a given target entity pair to help relation prediction. We develop a new neural RE method REDS2 in the multi-instance learning paradigm, which adopts a hierarchical model structure to fuse information respectively from 1-hop DS and 2-hop DS. Extensive experimental results on a benchmark dataset show that REDS2 can consistently outperform various baselines across different settings by a substantial margin.
Anthology ID:
D19-1039
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
410–420
Language:
URL:
https://aclanthology.org/D19-1039
DOI:
10.18653/v1/D19-1039
Bibkey:
Cite (ACL):
Xiang Deng and Huan Sun. 2019. Leveraging 2-hop Distant Supervision from Table Entity Pairs for Relation Extraction. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 410–420, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Leveraging 2-hop Distant Supervision from Table Entity Pairs for Relation Extraction (Deng & Sun, EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1039.pdf
Code
 sunlab-osu/REDS2