A Text-Generated Method to Joint Extraction of Entities and Relations

Entity-relation extraction is a basic task in natural language processing, and recently, the use of deep-learning methods, especially the Long Short-Term Memory (LSTM) network, has achieved remarkable performance. However, most of the existing entity-relation extraction methods cannot solve the over...

Full description

Saved in:
Bibliographic Details
Published inApplied sciences Vol. 9; no. 18; p. 3795
Main Authors E, Haihong, Xiao, Siqi, Song, Meina
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.09.2019
Subjects
Classification
Deep learning
entity recognition
information extraction
Knowledge
Long short-term memory
long short-term memory network
Natural language
Natural language processing
Neural networks
relation extraction
Semantics
Teaching methods
Online AccessGet full text

Cover

More Information
Summary:Entity-relation extraction is a basic task in natural language processing, and recently, the use of deep-learning methods, especially the Long Short-Term Memory (LSTM) network, has achieved remarkable performance. However, most of the existing entity-relation extraction methods cannot solve the overlapped multi-relation extraction problem, which means one or two entities are shared among multiple relational triples contained in a sentence. In this paper, we propose a text-generated method to solve the overlapped problem of entity-relation extraction. Based on this, (1) the entities and their corresponding relations are jointly generated as target texts without any additional feature engineering; (2) the model directly generates the relational triples using a unified decoding process, and entities can be repeatedly presented in multiple triples to solve the overlapped-relation problem. We conduct experiments on two public datasets—NYT10 and NYT11. The experimental results show that our proposed method outperforms the existing work, and achieves the best results.
ISSN:2076-3417
2076-3417
DOI:10.3390/app9183795