论文信息 - Chinese and Korean Cross-Lingual Issue News Detection based on Translation Knowledge of Wikipedia

Chinese and Korean Cross-Lingual Issue News Detection based on Translation Knowledge of Wikipedia

Cross-lingual issue news and analyzing the news content is an important and challenging task. The core of the cross-lingual research is the process of translation. In this paper, we focus on extracting cross-lingual issue news from the Twitter data of Chinese and Korean. We propose translation knowledge method for Wikipedia concepts as well as the Chinese and Korean cross-lingual inter-Wikipedia link relations. The relevance relations are extracted from the category and the page title of Wikipedia. The evaluation achieved a performance of 83 % in average precision in the top 10 extracted issue news. The result indicates that our method is an effective for cross-lingual issue news detection.

Shengnan Zhao | Kyung-Soon Lee | Bayar Tsolmon | Young-Seok Lee

[1] ChengXiang Zhai,et al. Cross-Lingual Latent Topic Extraction , 2010, ACL.

[2] Christiane Fellbaum,et al. Combining Local Context and Wordnet Similarity for Word Sense Identification , 1998 .

[3] D. Rubin,et al. Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[4] Andrew Trotman,et al. Overview of the NTCIR-9 Crosslink Task: Cross-lingual Link Discovery , 2011, NTCIR.

[5] Hosung Park,et al. What is Twitter, a social network or a news media? , 2010, WWW '10.

[6] Simone Paolo Ponzetto,et al. WikiRelate! Computing Semantic Relatedness Using Wikipedia , 2006, AAAI.

[7] Ying Zhang,et al. Domain-Specific Query Translation for Multilingual Information Access using Machine Translation Augmented With Dictionaries Mined from Wikipedia , 2008, IJCNLP.