WCSE

A Framework for Domain-specific Distant Supervised Named Entity Recognition

Abstract— With the development of knowledge graphs in the industrial field, Constructing KGs from domain-specific problems is greatly important. However, there is no consensus in regard to a plausible and definition of entities and relationships in the domain-specific knowledge graph. Further, in conjunction with several limitations and deficiencies, various domain-specific entities and relationships recognition approaches are far from perfect. Specifically, named entity recognition in domain-specific is a critical task for the natural language process applications. However, a bottleneck problem with named entity recognition in domain-specific is the lack of annotated data. To address this challenge, A domain-specific distant supervised named entity recognition framework is proposed. The framework is divided into two stages: first, the distant supervised corpus is generated based on the entity linking model of graph attention neural network; secondly, the generated corpus is trained as the input of the distant supervid named entity recognition model to train to obtain named entities. The link model is verified in the ccks2019 entity link corpus, and the F1 value is 2% higher than that of the benchmark method. The re-pre-trained BERT language model is added to the benchmark method, and the results show that it is more suitable for distant supervised named entity recognition tasks. Finally, it is applied in the computer field, and the results show that this framework can obtain domain named entities.

Index Terms— distant named entity recognition, entity linking, knowledge graph, graph attention neural network

Long Qin
Xi'an University of Posts and Telecommunications
Xiaoge Li
Xi'an University of Posts and Telecommunications

[Download]

Cite: Long Qin, Xiaoge Li, "A Framework for Domain-specific Distant Supervised Named Entity Recognition," WCSE 2022 Spring Event: 2022 9th International Conference on Industrial Engineering and Applications, pp. 18-29, Sanya, China, April 15-18, 2022.