@techreport{oai:ipsj.ixsq.nii.ac.jp:00185064,
 author = {Renzhi, Wang and Mizuho, Iwaihara and Renzhi, Wang and Mizuho, Iwaihara},
 issue = {15},
 month = {Dec},
 note = {Wikipedia is the largest online encyclopedia, in which articles are edited by different volunteers with different thoughts and styles. Sometimes two or more articles' titles are different but the themes of these articles are exactly the same or strongly similar. Administrators and editors are supposed to detect these article pairs and determine whether they should be merged together. In this paper, we propose a method to automatically determine whether an article pair should be merged together. We consider both duplicate case and overlap case. In the duplicate case, the articles pairs are covering exactly the same contents. In the overlap case, the articles pairs are covering related subjects that have a significant overlap. The content of an overlap part is similar but the words in the pair are probably different, so methods that exploit semantic relatedness are necessary. To deal with this problem we propose combination of multiple embedding results and rebuild word vectors for detecting mergeable article pairs. We also deal with various mergeable cases by combining distinct text fragments together. Our experiments show that our method performs better than existing embedding methods., Wikipedia is the largest online encyclopedia, in which articles are edited by different volunteers with different thoughts and styles. Sometimes two or more articles' titles are different but the themes of these articles are exactly the same or strongly similar. Administrators and editors are supposed to detect these article pairs and determine whether they should be merged together. In this paper, we propose a method to automatically determine whether an article pair should be merged together. We consider both duplicate case and overlap case. In the duplicate case, the articles pairs are covering exactly the same contents. In the overlap case, the articles pairs are covering related subjects that have a significant overlap. The content of an overlap part is similar but the words in the pair are probably different, so methods that exploit semantic relatedness are necessary. To deal with this problem we propose combination of multiple embedding results and rebuild word vectors for detecting mergeable article pairs. We also deal with various mergeable cases by combining distinct text fragments together. Our experiments show that our method performs better than existing embedding methods.},
 title = {Detection of mergeable Wikipedia articles based on multiple embedding results},
 year = {2017}
}