A Survey on Neural Open Information Extraction: Current Status and Future Directions

• DOI: 10.24963/ijcai.2022/793
• Publication Date: 2022-07-16T02:55:56Z
• Authors: Shaowen Zhou; Bowen Yu; Aixin Sun; Cheng Long; Jingyang Li; Jian Sun
• Keywords: Scope (computer science); Open domain; Open research

Open Information Extraction (OpenIE) facilitates domain-independent discovery of relational facts from large corpora. The technique well suits many open-world natural language understanding scenarios, such as automatic knowledge base construction, open-domain question answering, and explicit reasoning. Thanks to the rapid development in deep learning technologies, numerous neural OpenIE architectures have been proposed achieve considerable performance improvement. In this survey, we provide an extensive overview state-of-the-art models, their key design decisions, strengths weakness. Then, discuss limitations current solutions open issues problem itself. Finally list recent trends that could help expand its scope applicability, setting up promising directions for future research OpenIE. To our best knowledge, paper is first review on