Release Time:2019-03-11  Hits:

Indexed by: Journal Article

Date of Publication: 2017-01-01

Journal: Journal of Information Hiding and Multimedia Signal Processing

Included Journals: EI

Volume: 8

Issue: 2

Page Number: 358-367

ISSN: 20734212

Abstract: For the context of entity relation instance in TCM acupuncture and moxibustion field, effective words, syntax and semantics features are chosen to combine into feature template, and the entity relation instances are vectorized. The classification models of entity relations in TCM acupuncture and moxibustion area are trained by the machine learning method which is based on support vector machine. The experimental results show that the feature template of entity relations in this thesis have excellent effects on the entity relation extraction in TCM acupuncture and moxibustion area. The F-measure of entity relation classification model of DM, HM, AM and DRM reached 93.25%, 87.19%, 86.57%and84.57% respectively. © 2017 ISSN.