Zero-pronoun Data Augmentation for Japanese-to-English Translation
This work addresses a specific problem in Japanese-to-English translation for conversational domains, but it is incremental as it builds on existing data augmentation techniques.
The paper tackled the challenge of translating zero pronouns from Japanese to English by proposing a data augmentation method that uses local context to provide training signals, resulting in significant improvements in zero pronoun translation accuracy in conversational machine translation.
For Japanese-to-English translation, zero pronouns in Japanese pose a challenge, since the model needs to infer and produce the corresponding pronoun in the target side of the English sentence. However, although fully resolving zero pronouns often needs discourse context, in some cases, the local context within a sentence gives clues to the inference of the zero pronoun. In this study, we propose a data augmentation method that provides additional training signals for the translation model to learn correlations between local context and zero pronouns. We show that the proposed method significantly improves the accuracy of zero pronoun translation with machine translation experiments in the conversational domain.