Unsupervised Multilingual Alignment using Wasserstein Barycenter
This addresses the challenge of improving translation quality in multilingual alignment for NLP applications, though it appears incremental as it builds on existing alignment strategies.
The paper tackles the problem of unsupervised multilingual word alignment without parallel data by proposing the use of Wasserstein barycenter as a mean language to avoid degradation from poor pivot choices, achieving state-of-the-art results on standard benchmarks.
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.