Cross Lingual Adaptation: An Experiment on Sentiment Classifications

11 years 4 months ago
Cross Lingual Adaptation: An Experiment on Sentiment Classifications
In this paper, we study the problem of using an annotated corpus in English for the same natural language processing task in another language. While various machine translation systems are available, automated translation is still far from perfect. To minimize the noise introduced by translations, we propose to use only key `reliable" parts from the translations and apply structural correspondence learning (SCL) to find a low dimensional representation shared by the two languages. We perform experiments on an EnglishChinese sentiment classification task and compare our results with a previous cotraining approach. To alleviate the problem of data sparseness, we create extra pseudo-examples for SCL by making queries to a search engine. Experiments on real-world on-line review data demonstrate the two techniques can effectively improve the performance compared to previous work.
Bin Wei, Christopher Pal
Added 10 Feb 2011
Updated 10 Feb 2011
Type Journal
Year 2010
Where ACL
Authors Bin Wei, Christopher Pal
Comments (0)