Issue |
MATEC Web Conf.
Volume 100, 2017
13th Global Congress on Manufacturing and Management (GCMM 2016)
|
|
---|---|---|
Article Number | 02055 | |
Number of page(s) | 10 | |
Section | Part 2: Internet +, Big data and Flexible manufacturing | |
DOI | https://doi.org/10.1051/matecconf/201710002055 | |
Published online | 08 March 2017 |
Chinese and Thai Bilingual Topic Detection Online
1 School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China
2 The Key Laboratory of Intelligent Information Processing, Kunming University of Science and Technology, Kunming, Yunnan 650500, China
3 Information Management Center, Yunnan University Of Finance And Economics, Kunming, Yunnan 650500, China
* Corresponding E-mail: 915090822@qq.com
Bilingual topic detection is a vital application of natural language processing in the Internet plus Era and trend of economic globalization. At present, the method of bilingual topic detection can’t solve the problem of bilingual topic inconsistent distribution. Aiming at the shortcoming, this paper introduces a based on maximal clique method to find bilingual topic detection of Chinese and Thai feature words. First of all, extract the information of news with keywords of each Chinese and Thai documents through the TextRank algorithm. Next, disambiguate by means of the similarity combined with Chinese and Thai dictionary. Then, use credible association rules to cluster Chinese and Thai feature words, which generates maximal clique of bilingual topic. Finally, cluster similar maximal clique of topic to obtain the collection of final topic. According to the needs of users, the method can recommend a bilingual topic of different sizes. The test of Chinese and Thai news texts in January 2016 made good achievement. From the perspective of cross-language word clustering, the algorithm effectively solves the problem of inconsistency of bilingual topic distribution reasonably, and has the advantages of no need to estimate the number of topics and low time complexity, so it is suitable for the application of online discovery in ilingual topic.
Key words: Chinese / Thai / maximal cliques / credible association rule / TextRank / bilingual topics detection
© The Authors, published by EDP Sciences, 2017
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.