The TALP-UPC Neural Machine Translation System for German/Finnish-English Using the Inverse Direction Model in Rescoring

摘要

In this paper, we describe the TALP-UPC participation in the News Task for German-English and Finish-English. Our primary submission implements a fully character to character neural machine translation architecture with an additional rescoring of a n-best list of hypothesis using a forced back-translation to the source sentence. This model gives consistent improvements on different pairs of languages for the language direction with the lowest performance while keeping the quality in the direction with the highest performance. Additional experiments are reported for multilingual character to character neural machine translation, phrase-based translation and the additional Turkish-English language pair.