A Multi-task Approach to Learning Multilingual Representations
We present a novel multi-task modeling approach to learning multilingual distributed representations of text. Our system learns word and sentence embeddings jointly by training a multilingual skip-gram model together with a cross-lingual sentence similarity model. Our architecture can transparently use both monolingual and sentence aligned bilingual corpora to learn multilingual embeddings, thus covering a vocabulary significantly larger than the vocabulary of the bilingual corpora alone. Our model shows competitive performance in a standard cross-lingual document classification task. We also show the effectiveness of our method in a limited resource scenario.