Search

Your search keyword '"credible association rule"' showing total 3 results
Start Over Descriptor "credible association rule"
3 results on '"credible association rule"'

1. A practical approach to topic detection based on credible association rule mining.

Author

Wu, Lihua, Xiao, Bo, Lin, Zhiqing, and Lu, Yueming

Abstract

Topic detection is to develop automatic methods to identify topically related documents within a stream of data; many approaches have been developed to classify documents with predefined knowledge. This paper presents a new approach for topic detection and tracking based on credible association rule (CAR). This paper considers topic detection without any prior knowledge of category structure or possible categories. Topic features are selected primarily based on CAR. Results on the test set show a marginal improvement by using CAR and its maximal cliques mining algorithm. The CAR maximal cliques mining algorithm is now applied on real topic detection and tracking system which gives us a lot of experience in adjusting and refining the algorithm. This algorithm also presents many useful interface extensions for other modules of the system to use. [ABSTRACT FROM PUBLISHER]

Published
2012
Full Text
View/download PDF

2. Chinese and Thai Bilingual Topic Detection Online

Author

Rang Ziqiang, Zhou Lanjiang, Zhang Jinpeng, Xian Yantuan, and Yu Zhengtao

Subjects
Chinese, Thai, maximal cliques, credible association rule, TextRank, bilingual topics detection, Engineering (General). Civil engineering (General), TA1-2040
Abstract

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.

Published
2017
Full Text
View/download PDF

3. Chinese and Thai Bilingual Topic Detection Online

Author

Lanjiang Zhou, Zhengtao Yu, Jinpeng Zhang, Yantuan Xian, and Ziqiang Rang

Subjects
Association rule learning, Computer science, 0211 other engineering and technologies, 02 engineering and technology, computer.software_genre, 0203 mechanical engineering, credible association rule, 021105 building & construction, Similarity (psychology), bilingual topics detection, Feature (machine learning), TextRank, Cluster analysis, Time complexity, Clique, Chinese, business.industry, maximal cliques, 020303 mechanical engineering & transports, lcsh:TA1-2040, The Internet, Artificial intelligence, business, Thai, lcsh:Engineering (General). Civil engineering (General), computer, Word (computer architecture), Natural language processing
Abstract

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.

Published
2017

Catalog

Books, media, physical & digital resources
See catalog results