A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings
This addresses the challenge of cross-lingual mapping for NLP applications in realistic, unsupervised scenarios, representing a significant advance over prior methods.
The paper tackles the problem of learning cross-lingual word embeddings without parallel data by proposing a robust self-learning method that exploits structural similarity and iteratively improves solutions, achieving state-of-the-art results on standard datasets and surpassing previous supervised systems.
Recent work has managed to learn cross-lingual word embeddings without parallel data by mapping monolingual embeddings to a shared space through adversarial training. However, their evaluation has focused on favorable conditions, using comparable corpora or closely-related languages, and we show that they often fail in more realistic scenarios. This work proposes an alternative approach based on a fully unsupervised initialization that explicitly exploits the structural similarity of the embeddings, and a robust self-learning algorithm that iteratively improves this solution. Our method succeeds in all tested scenarios and obtains the best published results in standard datasets, even surpassing previous supervised systems. Our implementation is released as an open source project at https://github.com/artetxem/vecmap