Contextual Neural Machine Translation Improves Translation of Cataphoric Pronouns
This work addresses a specific issue in machine translation for languages with cataphoric pronouns, representing an incremental improvement over existing contextual methods.
The paper tackled the problem of improving translation of cataphoric pronouns in neural machine translation by investigating the use of future sentences as context, showing that this approach achieves significant improvements over context-agnostic models and comparable or better performance than using past context, with reported gains in BLEU scores.
The advent of context-aware NMT has resulted in promising improvements in the overall translation quality and specifically in the translation of discourse phenomena such as pronouns. Previous works have mainly focused on the use of past sentences as context with a focus on anaphora translation. In this work, we investigate the effect of future sentences as context by comparing the performance of a contextual NMT model trained with the future context to the one trained with the past context. Our experiments and evaluation, using generic and pronoun-focused automatic metrics, show that the use of future context not only achieves significant improvements over the context-agnostic Transformer, but also demonstrates comparable and in some cases improved performance over its counterpart trained on past context. We also perform an evaluation on a targeted cataphora test suite and report significant gains over the context-agnostic Transformer in terms of BLEU.