Quality-Aware Translation Models: Efficient Generation and Quality Estimation in a Single Model

arXiv:2310.06707v2 Announce Type: replace
Abstract: Maximum-a-posteriori (MAP) decoding is the most widely used decoding strategy for neural machine translation (NMT) models. The underlying assumption is that model probability correlates well with human judgment, with better translations getting assigned a higher score by the model. However, research has shown that this assumption does not always hold, and generation quality can be improved by decoding to optimize a utility function backed by a metric or quality-estimation signal, as is done by Minimum …

abstract arxiv cs.ai cs.cl decoding human judgment machine machine translation map neural machine translation probability quality research strategy translation type