Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism

Xiangrong Zeng, Daojian Zeng, Shizhu He, Kang Liu, Jun Zhao


Abstract
The relational facts in sentences are often complicated. Different relational triplets may have overlaps in a sentence. We divided the sentences into three types according to triplet overlap degree, including Normal, EntityPairOverlap and SingleEntiyOverlap. Existing methods mainly focus on Normal class and fail to extract relational triplets precisely. In this paper, we propose an end-to-end model based on sequence-to-sequence learning with copy mechanism, which can jointly extract relational facts from sentences of any of these classes. We adopt two different strategies in decoding process: employing only one united decoder or applying multiple separated decoders. We test our models in two public datasets and our model outperform the baseline method significantly.
Anthology ID:
P18-1047
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
506–514
Language:
URL:
https://aclanthology.org/P18-1047
DOI:
10.18653/v1/P18-1047
Bibkey:
Cite (ACL):
Xiangrong Zeng, Daojian Zeng, Shizhu He, Kang Liu, and Jun Zhao. 2018. Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 506–514, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism (Zeng et al., ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-1047.pdf
Poster:
 P18-1047.Poster.pdf
Data
NYT11-HRLNew York Times Annotated CorpusWebNLG