19 papers with code • 0 benchmarks • 0 datasets
Translate words from one language to another.
Our approach decouples learning the transformation from the source language to the target language into (a) learning rotations for language-specific embeddings to align them to a common space, and (b) learning a similarity metric in the common space to model similarities between the embeddings.
In this paper, we propose a self-supervised method to refine the alignment of unsupervised bilingual word embeddings.
A recent research line has obtained strong results on bilingual lexicon induction by aligning independently trained word embeddings in two languages and using the resulting cross-lingual embeddings to induce word translation pairs through nearest neighbor or related retrieval methods.
Supervised methods for this problem rely on the availability of cross-lingual supervision, either using parallel corpora or bilingual lexicons as the labeled data for training, which may not be available for many low resource languages.
Recent advances in BLI work by aligning the two word embedding spaces.
We introduce a novel discriminative latent-variable model for the task of bilingual lexicon induction.
We propose a new approach for learning contextualised cross-lingual word embeddings based only on a small parallel corpus (e. g. a few hundred sentence pairs).
We then propose Bilingual Lexicon Induction with Semi-Supervision (BLISS) --- a semi-supervised approach that relaxes the isometric assumption while leveraging both limited aligned bilingual lexicons and a larger set of unaligned word embeddings, as well as a novel hubness filtering technique.