Chinese Auto-Clustering of Oral Conversation Corpus Based on Contextual Features

Yue Chen, Qi Chen, Minghu JiangSignal 2015 · DOI

Abstract

Chinese text clustering requires more linguistic knowledge in order to understand and analyze natural language accurately. To improve the accuracy of such clustering, in this article, we adopt SOM algorithm to add contextual features into the process of Chinese auto-clustering of oral corpus based on a contextual dictionary, and testify the effect of such a pragmatic application.
BibTeX
@inproceedings{chen2015chinese,
  author = {Yue Chen and Qi Chen and Minghu Jiang},
  title = {{Chinese Auto-Clustering of Oral Conversation Corpus Based on Contextual Features}},
  booktitle = {Signal},
  year = {2015},
  doi = {10.14355/spr.2015.04.004},
}

Loading related content...

Figure