Analyzing the Use of Character-Level Translation with Sparse and Noisy Datasets
This addresses translation challenges for low-resource languages using noisy data, but it is incremental as it builds on existing pivot-based methods.
The paper tackles the problem of machine translation on sparse and noisy datasets, such as crowdsourced subtitles, by analyzing character-level models in pivot-based translation, finding they reduce untranslated words by over 40% and improve BLEU scores by 2-3 points with limited data.
This paper provides an analysis of character-level machine translation models used in pivot-based translation when applied to sparse and noisy datasets, such as crowdsourced movie subtitles. In our experiments, we find that such character-level models cut the number of untranslated words by over 40% and are especially competitive (improvements of 2-3 BLEU points) in the case of limited training data. We explore the impact of character alignment, phrase table filtering, bitext size and the choice of pivot language on translation quality. We further compare cascaded translation models to the use of synthetic training data via multiple pivots, and we find that the latter works significantly better. Finally, we demonstrate that neither word-nor character-BLEU correlate perfectly with human judgments, due to BLEU's sensitivity to length.