Exploring different representational units in English-to-Turkish statistical machine translation

We investigate different representational granularities for sub-lexical representation in statistical machine translation work from English to Turkish. We find that (i) representing both Turkish and English at the morpheme-level but with some selective morpheme-grouping on the Turkish side of the training data, (ii) augmenting the training data with “sentences” comprising only the content words of the original training data to bias root word alignment, (iii) reranking the n-best morpheme-sequence outputs of the decoder with a word-based language model, and (iv) using model iteration all provide a non-trivial improvement over a fully word-based baseline. Despite our very limited training data, we improve from 20.22 BLEU points for our simplest model to 25.08 BLEU points for an improvement of 4.86 points or 24% relative.