Contrastive Learning for Context-aware Neural Machine TranslationUsing Coreference Information

Abstract

Context-aware neural machine translation (NMT) incorporates contextual information of surrounding texts, that can improve the translation quality of document-level machine translation. Many existing works on context-aware NMT have focused on developing new model architectures for incorporating additional contexts and have shown some promising results. However, most existing works rely on crossentropy loss, resulting in limited use of contextual information. In this paper, we propose CorefCL, a novel data augmentation and contrastive learning scheme based on coreference between the source and contextual sentences. By corrupting automatically detected coreference mentions in the contextual sentence, CorefCL can train the model to be sensitive to coreference inconsistency. We experimented with our method on common context-aware NMT models and two document-level translation tasks. In the experiments, our method consistently improved BLEU of compared models on English-German and English-Korean tasks. We also show that our method significantly improves coreference resolution in the English-German contrastive test suite.

Ask Language Model to Clean Your Noisy Translation Data

“…In addition to the straightforward training on newly constructed sets, we also train models with contrastive learning, which is inspired by previous works Hwang et al, 2021;Hu and Li, 2022) that recognize the effectiveness of contrastive learning in improving the robustness of NLP and NMT models. By employing this method, we can analyze the performance of C-MTNT on a wider range of models trained with different approaches and settings.…”