Syntactic Multi-view Learning for Open Information Extraction

Autor:	Dong, Kuicai, Sun, Aixin, Kim, Jung-Jae, Li, Xiaoli
Rok vydání:	2022
Předmět:	Computer Science - Computation and Language Computer Science - Artificial Intelligence
Zdroj:	EMNLP 2022
Druh dokumentu:	Working Paper
Popis:	Open Information Extraction (OpenIE) aims to extract relational tuples from open-domain sentences. Traditional rule-based or statistical models have been developed based on syntactic structures of sentences, identified by syntactic parsers. However, previous neural OpenIE models under-explore 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 both 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. Comment: To appear in EMNLP 2022
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2212.02068 Zobrazit plný text záznamu View this record from Arxiv