Trans-gram, Fast Cross-lingual Word-embeddings
This addresses the challenge of cross-lingual NLP for researchers and practitioners by providing a fast and effective method for multilingual word embeddings.
The authors tackled the problem of learning and aligning word embeddings across multiple languages efficiently, achieving state-of-the-art results on cross-lingual text classification and word translation tasks.
We introduce Trans-gram, a simple and computationally-efficient method to simultaneously learn and align wordembeddings for a variety of languages, using only monolingual data and a smaller set of sentence-aligned data. We use our new method to compute aligned wordembeddings for twenty-one languages using English as a pivot language. We show that some linguistic features are aligned across languages for which we do not have aligned data, even though those properties do not exist in the pivot language. We also achieve state of the art results on standard cross-lingual text classification and word translation tasks.