Difference between revisions of "Mining New Translation Lexicons from Wikipedia"
(New study: Mining New Translation Lexicons from Wikipedia) |
(+ links) |
||
Line 1: | Line 1: | ||
− | '''Mining New Translation Lexicons from Wikipedia''' - scientific work related to Wikipedia quality published in 2007, written by Jong-Hoon Oh, Daisuke Kawahara, Kiyotaka Uchimoto and Hitoshi Isahara. | + | '''Mining New Translation Lexicons from Wikipedia''' - scientific work related to [[Wikipedia quality]] published in 2007, written by [[Jong-Hoon Oh]], [[Daisuke Kawahara]], [[Kiyotaka Uchimoto]] and [[Hitoshi Isahara]]. |
== Overview == | == Overview == | ||
− | In this paper, authors propose a method of mining new translation lexicons from Wikipedia. To do this, first a network is constructed with nodes representing Wikipedia articles and links representing the dependencies between the articles. Then authors learn a model of translation lexicons by investigating co-occurrence patterns of the existing translation lexicons in a Wikipedia network. Finally, new translation lexicons can be found by estimating the cross-lingual similarities between the nodes in different | + | In this paper, authors propose a method of mining new translation lexicons from [[Wikipedia]]. To do this, first a network is constructed with nodes representing Wikipedia articles and links representing the dependencies between the articles. Then authors learn a model of translation lexicons by investigating co-occurrence patterns of the existing translation lexicons in a Wikipedia network. Finally, new translation lexicons can be found by estimating the [[cross-lingual]] similarities between the nodes in [[different language]]s. Experiments show that method effectively finds new translation lexicons. |
Revision as of 10:38, 27 November 2019
Mining New Translation Lexicons from Wikipedia - scientific work related to Wikipedia quality published in 2007, written by Jong-Hoon Oh, Daisuke Kawahara, Kiyotaka Uchimoto and Hitoshi Isahara.
Overview
In this paper, authors propose a method of mining new translation lexicons from Wikipedia. To do this, first a network is constructed with nodes representing Wikipedia articles and links representing the dependencies between the articles. Then authors learn a model of translation lexicons by investigating co-occurrence patterns of the existing translation lexicons in a Wikipedia network. Finally, new translation lexicons can be found by estimating the cross-lingual similarities between the nodes in different languages. Experiments show that method effectively finds new translation lexicons.