%0 Conference Paper %1 Yucesoy07semanticSimilarity %A Yucesoy, B. %A Oguducu, S.G. %B Machine Learning and Applications, 2007. ICMLA 2007. Sixth International Conference on %D 2007 %K 07 Yucesoy clustering semantic similarity term turkish %P 393-398 %R 10.1109/ICMLA.2007.52 %T Comparison of semantic and single term similarity measures for clustering turkish documents %U http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?tp=&arnumber=4457262&isnumber=4457184 %X With the rapid growth of the World Wide Web (www), it becomes a critical issue to design and organize the vast amounts of on-line documents on the web according to their topic. Even for the search engines it is very important to group similar documents in order to improve their performance when a query is submitted to the system. Clusterng is useful for taxonomy design and similarity search of documents on such a domain. Similarity is fundamental to many clustering applications on hypertext. In this paper, we will study how measures of similarity are used to cluster a collection of documents on a web site. Most of the document clustering techniques rely on single term analysis of text, such as vector space model. To better group of related documents we propose a new semantic similarity measure. We compare our measure with Wu-Palmer similarity and cosine similarity. Experimental results show that cosine similarity perform better than the semantic similarities. We demonstrate our results on Turkish documents. This is a first study that considers the semantic similarities between Turkish documents.

@inproceedings{Yucesoy07semanticSimilarity, abstract = {With the rapid growth of the World Wide Web (www), it becomes a critical issue to design and organize the vast amounts of on-line documents on the web according to their topic. Even for the search engines it is very important to group similar documents in order to improve their performance when a query is submitted to the system. Clusterng is useful for taxonomy design and similarity search of documents on such a domain. Similarity is fundamental to many clustering applications on hypertext. In this paper, we will study how measures of similarity are used to cluster a collection of documents on a web site. Most of the document clustering techniques rely on single term analysis of text, such as vector space model. To better group of related documents we propose a new semantic similarity measure. We compare our measure with Wu-Palmer similarity and cosine similarity. Experimental results show that cosine similarity perform better than the semantic similarities. We demonstrate our results on Turkish documents. This is a first study that considers the semantic similarities between Turkish documents.}, added-at = {2010-01-26T03:41:30.000+0100}, author = {Yucesoy, B. and Oguducu, S.G.}, biburl = {https://www.bibsonomy.org/bibtex/2b87f04dd555f54a9cba00d716ed0902b/lee_peck}, booktitle = {Machine Learning and Applications, 2007. ICMLA 2007. Sixth International Conference on}, description = {Welcome to IEEE Xplore 2.0: Comparison of semantic and single term similarity measures for clustering turkish documents}, doi = {10.1109/ICMLA.2007.52}, interhash = {d5a1574e478339a5de103178d0ac2e1d}, intrahash = {b87f04dd555f54a9cba00d716ed0902b}, keywords = {07 Yucesoy clustering semantic similarity term turkish}, month = {Dec.}, pages = {393-398}, timestamp = {2010-01-26T03:41:30.000+0100}, title = {Comparison of semantic and single term similarity measures for clustering turkish documents}, url = {http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?tp=&arnumber=4457262&isnumber=4457184}, year = 2007 }