Recent neural network models have achieved impressive performance on sentiment classification in English as well as other languages . Their success heavily depends on the availability of a large amount of labeled data or parallel corpus . In this paper, we investigate an extreme scenario of cross-lingual sentiment classification, in which the low-resource language does not have any labels or parallel . We propose an unsupervised . model named . multi-view encoder-classifier (MVEC) that leverages an un .supervised machine translation (UMT) system and a language discriminator . Extensive experiments on five language pairs verify that our model significantly outperforms other . models for 8/11 sentiment classification tasks . Our model significantly outranks other models for eight/11 targets tasks in English as to the classification tasks. Extensive experiments

Links: PDF - Abstract

Code :

None

Keywords : classification - sentiment - language - models - tasks -

Leave a Reply

Your email address will not be published. Required fields are marked *