SwitchNet: A modular neural network for adaptive relation extraction

• Published in: Computers & electrical engineering Vol. 104; no. B; p. 108445
• Main Authors: Zhu, Hongyin, Tiwari, Prayag, Zhang, Yazhou, Gupta, Deepak, Alharbi, Meshal, Nguyen, Tri Gia, Dehdashti, Shahram
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.12.2022
• Subjects: Entity pair; Information flow; Joint optimization; Modular neural network; Relation extraction; Relation extraction; Entity pair; Joint optimization; Information flow; Modular neural network
• ISSN: 0045-7906; 1879-0755; 1879-0755
• DOI: 10.1016/j.compeleceng.2022.108445

This paper presents a portable toolkit, SwitchNet, for extracting relations from textual input. We summarize four data protocols for relation extraction tasks, including relation classification, relation extraction, triple extraction, and distant supervision relation extraction. This neural architecture is modular, so it can take as input data at different stages of the information extraction process (simple text, text and entities or entity pairs as relation candidates) and compute the rest of the process (named entity recognition and relation classification). We systematically design four information flows to integrate the above protocols by sharing network building blocks and switching different information flows. This framework can extract multiple triples (subject, predicate, object) in one pass. This framework enhances the use of relation classification models in end-to-end triple extraction by inferring pairs of entities of interest and using the shared representation mechanism. [Display omitted] •Dividing the information extraction process into modular neural networks.•4 information flows for integrating 4 relation extraction data protocols.•Integrating NER and RE subtasks through the POEOI inference.•Performance improvements for 4 relation extraction tasks.