Cross-Sentence N-ary Relation Extraction using Lower-Arity Universal Schemas

Kosuke Akimoto, Takuya Hiraoka, Kunihiko Sadamasa, Mathias Niepert


Abstract
Most existing relation extraction approaches exclusively target binary relations, and n-ary relation extraction is relatively unexplored. Current state-of-the-art n-ary relation extraction method is based on a supervised learning approach and, therefore, may suffer from the lack of sufficient relation labels. In this paper, we propose a novel approach to cross-sentence n-ary relation extraction based on universal schemas. To alleviate the sparsity problem and to leverage inherent decomposability of n-ary relations, we propose to learn relation representations of lower-arity facts that result from decomposing higher-arity facts. The proposed method computes a score of a new n-ary fact by aggregating scores of its decomposed lower-arity facts. We conduct experiments with datasets for ternary relation extraction and empirically show that our method improves the n-ary relation extraction performance compared to previous methods.
Anthology ID:
D19-1645
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
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
6225–6231
Language:
URL:
https://aclanthology.org/D19-1645
DOI:
10.18653/v1/D19-1645
Bibkey:
Cite (ACL):
Kosuke Akimoto, Takuya Hiraoka, Kunihiko Sadamasa, and Mathias Niepert. 2019. Cross-Sentence N-ary Relation Extraction using Lower-Arity Universal Schemas. 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 6225–6231, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Cross-Sentence N-ary Relation Extraction using Lower-Arity Universal Schemas (Akimoto et al., EMNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1645.pdf
Attachment:
 D19-1645.Attachment.zip