Syntactic Multi-view Learning for Open Information Extraction

Kuicai Dong, Aixin Sun, Jung-Jae Kim, Xiaoli Li


Abstract
Open Information Extraction (OpenIE) aims to extract relational tuples from open-domain sentences. Traditional rule-based or statistical models were developed based on syntactic structure of sentence, identified by syntactic parsers. However, previous neural OpenIE models under-explored the useful syntactic information. In this paper, we model both constituency and dependency trees into word-level graphs, and enable neural OpenIE to learn from the syntactic structures. To better fuse heterogeneous information from the two graphs, we adopt multi-view learning to capture multiple relationships from them. Finally, the finetuned constituency and dependency representations are aggregated with sentential semantic representations for tuple generation. Experiments show that both constituency and dependency information, and the multi-view learning are effective.
Anthology ID:
2022.emnlp-main.272
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4072–4083
Language:
URL:
https://aclanthology.org/2022.emnlp-main.272
DOI:
10.18653/v1/2022.emnlp-main.272
Bibkey:
Cite (ACL):
Kuicai Dong, Aixin Sun, Jung-Jae Kim, and Xiaoli Li. 2022. Syntactic Multi-view Learning for Open Information Extraction. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 4072–4083, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Syntactic Multi-view Learning for Open Information Extraction (Dong et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.272.pdf