Automatic Bilingual Phrase Dictionary Construction from GIZA++ Output

Abstract

Modern encoder-decoder based neural machine translation (NMT) models are normally trained on parallel sentences. Hence, they give best results when translating full sentences rather than sentence parts. Thereby, the task of translating commonly used phrases, which often arises for language learners, is not addressed by NMT models. While for high-resourced language pairs human-built phrase dictionaries exist, less-resourced pairs do not have them. We suggest an approach for building such dictionary automatically based on the GIZA++ output and show that it works significantly better than translating phrases with a sentences-trained NMT system.