Unsupervised Multilingual Alignment using Wasserstein Barycenter
arXiv:2002.00743 · doi:10.24963/ijcai.2020/512
Abstract
We study unsupervised multilingual alignment, the problem of finding word-to-word translations between multiple languages without using any parallel data. One popular strategy is to reduce multilingual alignment to the much simplified bilingual setting, by picking one of the input languages as the pivot language that we transit through. However, it is well-known that transiting through a poorly chosen pivot language (such as English) may severely degrade the translation quality, since the assumed transitive relations among all pairs of languages may not be enforced in the training process. Instead of going through a rather arbitrarily chosen pivot language, we propose to use the Wasserstein barycenter as a more informative "mean" language: it encapsulates information from all languages and minimizes all pairwise transportation costs. We evaluate our method on standard benchmarks and demonstrate state-of-the-art performances.
arXiv commentCode is available at https://github.com/alixxxin/multi-lang
References in corpus (11)
- Distributed Representations of Words and Phrases and their Compositionality
- Exploiting Similarities among Languages for Machine Translation
- A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings
- Fast Computation of Wasserstein Barycenters
- BilBOWA: Fast Bilingual Distributed Representations without Word Alignments
- Offline bilingual word vectors, orthogonal transformations and the inverted softmax
- Word Translation Without Parallel Data
- Unsupervised Hyperalignment for Multilingual Word Embeddings
- Stochastic Wasserstein Barycenters
- Unsupervised Alignment of Embeddings with Wasserstein Procrustes
- Unsupervised Multilingual Alignment using Wasserstein Barycenter