DMCA
Semi-Supervised Representation Learning for Cross-Lingual Text Classification
BibTeX
@MISC{Xiao_semi-supervisedrepresentation,
author = {Min Xiao and Yuhong Guo},
title = {Semi-Supervised Representation Learning for Cross-Lingual Text Classification},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Cross-lingual adaptation aims to learn a pre-diction model in a label-scarce target lan-guage by exploiting labeled data from a label-rich source language. An effective cross-lingual adaptation system can substantially re-duce the manual annotation effort required in many natural language processing tasks. In this paper, we propose a new cross-lingual adaptation approach for document classifica-tion based on learning cross-lingual discrim-inative distributed representations of words. Specifically, we propose to maximize the log-likelihood of the documents from both lan-guage domains under a cross-lingual log-bilinear document model, while minimizing the prediction log-losses of labeled docu-ments. We conduct extensive experiments on cross-lingual sentiment classification tasks of Amazon product reviews. Our experimental results demonstrate the efficacy of the pro-posed cross-lingual adaptation approach. 1
Keyphrases
cross-lingual text classification semi-supervised representation learning extensive experiment document classifica-tion labeled docu-ments new cross-lingual adaptation approach effective cross-lingual adaptation system experimental result manual annotation effort cross-lingual log-bilinear document model cross-lingual adaptation aim label-scarce target lan-guage cross-lingual sentiment classification task many natural language processing task label-rich source language prediction log-losses pro-posed cross-lingual adaptation approach lan-guage domain pre-diction model amazon product review cross-lingual discrim-inative distributed representation
