Presentation 2013-06-22
Language-independent Short Text Similarity Measurements Using the Vector of Wikipedia Articles
Tatsuya NAKAMURA, Masumi SHIRAKAWA, Takahiro HARA, Shojiro NISHIO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we proposed a language-independent method to measure similarity between short texts written in different languages by unifying the language space using Wikipedia. In recent years, immediacy and locality of information dissemination have been regarded as important, and people around the world have been continuously transmitting information about their local area in their own languages. However, measuring similarity between these texts is difficult because they are short and written in various languages. Our method solves this problem by representing short texts written in any languages using the vector of a certain language Wikipedia articles. From the experimental results, we confirmed that our method significantly outperformed comparative methods.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Wikipedia / Text Similarity / Short Text Analysis / Multi-lingual Information Retrieval
Paper # DE2013-15
Date of Issue

Conference Information
Committee DE
Conference Date 2013/6/15(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Data Engineering (DE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Language-independent Short Text Similarity Measurements Using the Vector of Wikipedia Articles
Sub Title (in English)
Keyword(1) Wikipedia
Keyword(2) Text Similarity
Keyword(3) Short Text Analysis
Keyword(4) Multi-lingual Information Retrieval
1st Author's Name Tatsuya NAKAMURA
1st Author's Affiliation Gradute School of Information Science and Technology, Osaka University()
2nd Author's Name Masumi SHIRAKAWA
2nd Author's Affiliation Gradute School of Information Science and Technology, Osaka University
3rd Author's Name Takahiro HARA
3rd Author's Affiliation Gradute School of Information Science and Technology, Osaka University
4th Author's Name Shojiro NISHIO
4th Author's Affiliation Gradute School of Information Science and Technology, Osaka University
Date 2013-06-22
Paper # DE2013-15
Volume (vol) vol.113
Number (no) 105
Page pp.pp.-
#Pages 6
Date of Issue