Study on Wikipedia for Translation Mining for Clir

From Wikipedia Quality
Revision as of 07:36, 25 July 2019 by Aubree (talk | contribs) (New work - Study on Wikipedia for Translation Mining for Clir)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

Study on Wikipedia for Translation Mining for Clir - scientific work related to Wikipedia quality published in 2010, written by Jianmin Yao, Chang-Long Sun, Yu Hong, Yun-Dong Ge and Qiaoming Zhu.

Overview

The query translation of Out of Vocabulary (OOV) is one of the key factors that affect the performance of Cross-Language Information Retrieval (CLIR). Based on Wikipedia data structure and language features, the paper divides translation environment into target-existence and target-deficit environment. To overcome the difficulty of translation mining in the target-deficit environment, the frequency change information and adjacency information is used to realize the extraction of candidate units, and establish the strategy of mixed translation mining based on the frequency-distance model, surface pattern matching model and summary-score model. Search engine based OOV translation mining is taken as baseline to test the performance on TOP1 results. It is verified that the mixed translation mining method based on Wikipedia can achieve the precision rate of 0.6279, and the improvement is 6.98% better than the baseline.

Retrieved from "https://wikipediaquality.com/index.php?title=Study_on_Wikipedia_for_Translation_Mining_for_Clir&oldid=19419"