Enhancing text clustering by leveraging Wikipedia semantics Export

@inproceedings{citeulike:3112647, abstract = {Most traditional text clustering methods are based on "bag of words" (BOW) representation based on frequency statistics in a set of documents. BOW, however, ignores the important information on the semantic relationships between key terms. To overcome this problem, several methods have been proposed to enrich text representation with external resource in the past, such as WordNet. However, many of these approaches suffer from some limitations: 1) WordNet has limited coverage and has a lack of effective word-sense disambiguation ability; 2) Most of the text representation enrichment strategies, which append or replace document terms with their hypernym and synonym, are overly simple. In this paper, to overcome these deficiencies, we first propose a way to build a concept thesaurus based on the semantic relations (synonym, hypernym, and associative relation) extracted from Wikipedia. Then, we develop a unified framework to leverage these semantic relations in order to enhance traditional content similarity measure for text clustering. The experimental results on Reuters and OHSUMED datasets show that with the help of Wikipedia thesaurus, the clustering performance of our method is improved as compared to previous methods. In addition, with the optimized weights for hypernym, synonym, and associative concepts that are tuned with the help of a few labeled data users provided, the clustering performance can be further improved.}, address = {New York, NY, USA}, author = {Hu, Jian and Fang, Lujun and Cao, Yang and Zeng, Hua-Jun and Li, Hua and Yang, Qiang and Chen, Zheng}, booktitle = {SIGIR '08: Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval}, citeulike-article-id = {3112647}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1390334.1390367}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1390334.1390367}, doi = {10.1145/1390334.1390367}, isbn = {978-1-60558-164-4}, keywords = {clustering, semantic\_relations, wikipedia--nlp\_resource}, location = {Singapore, Singapore}, pages = {179--186}, posted-at = {2008-08-12 20:18:03}, priority = {0}, publisher = {ACM}, title = {Enhancing text clustering by leveraging Wikipedia semantics}, url = {http://dx.doi.org/10.1145/1390334.1390367}, year = {2008} }

TY - CONF ID - citeulike:3112647 L3 - citeulike-article-id:3112647 N2 - Most traditional text clustering methods are based on "bag of words" (BOW) representation based on frequency statistics in a set of documents. BOW, however, ignores the important information on the semantic relationships between key terms. To overcome this problem, several methods have been proposed to enrich text representation with external resource in the past, such as WordNet. However, many of these approaches suffer from some limitations: 1) WordNet has limited coverage and has a lack of effective word-sense disambiguation ability; 2) Most of the text representation enrichment strategies, which append or replace document terms with their hypernym and synonym, are overly simple. In this paper, to overcome these deficiencies, we first propose a way to build a concept thesaurus based on the semantic relations (synonym, hypernym, and associative relation) extracted from Wikipedia. Then, we develop a unified framework to leverage these semantic relations in order to enhance traditional content similarity measure for text clustering. The experimental results on Reuters and OHSUMED datasets show that with the help of Wikipedia thesaurus, the clustering performance of our method is improved as compared to previous methods. In addition, with the optimized weights for hypernym, synonym, and associative concepts that are tuned with the help of a few labeled data users provided, the clustering performance can be further improved. CY - Singapore, Singapore SN - 978-1-60558-164-4 AD - New York, NY, USA EP - 186 TI - Enhancing text clustering by leveraging Wikipedia semantics PB - ACM T2 - SIGIR '08: Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval SP - 179 KW - clustering KW - semantic_relations KW - wikipedia--nlp_resource AU - Hu, Jian AU - Fang, Lujun AU - Cao, Yang AU - Zeng, Hua-Jun AU - Li, Hua AU - Yang, Qiang AU - Chen, Zheng PY - 2008/// UR - http://dx.doi.org/10.1145/1390334.1390367 ER -