A Bi-LSTM mention hypergraph model with encoding schema for mention extraction. (October 2019)

• Record Type: Journal Article
• Authors: Lin, Jerry Chun-Wei; Shao, Yinan; Zhou, Yujie; Pirouz, Matin; Chen, Hsing-Chung
• Is Part Of: Engineering applications of artificial intelligence. Volume 85(2019)
• Page Start: 175
• Page End: 181
• Publication Date: 2019-10
• Subjects: Neural network -- Bi-LSTM -- Sequence prediction -- Mention-hypergraph; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2019.06.005
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Natural language processing is a technique to process data such as text and speech. Some fundamental research includes named-entity recognition, which recognizes name entities (i.e., persons, companies) from texts; semantic parsing, which is used to convert a natural language utterance to the representation of logical form; and co-reference resolution, which extracts nouns (including pronouns, noun phrases) pointing to the same reference body. In this paper, we mainly focus on the task of mention extraction, which extract and classify overlapping or nested structure mentions. We proposed a neural-encoded mention-hypergraph (NEMH) model to use hypergraph to model overlapping or nested structure mentions and use neural networks to extract features for hypergraph automatically. Unlike the existing approaches, our hypergraph model can effectively capture nested mention entities with unlimited lengths. Also, the proposed model is highly scalable and the time complexity of the proposed model is linear in the number of mention classes and the number of input words. Extensive experiments are conducted on several standard datasets to demonstrate the effectiveness of the proposed model.