PROSE: A Pronoun Omission Solution for Chinese-English Spoken Language Translation
Submission Type: Regular Long Paper
Submission Track: Machine Translation
Submission Track 2: NLP Applications
Keywords: Chinese-English Spoken Language Translation, Zero-Pronoun, Mention-Aware Semantic Augmentation
TL;DR: Our study sheds light on the challenges posed by zero pronouns in Chinese-English spoken language translation and provides a valuable solution that can improve the performance of neural machine translation systems.
Abstract: Neural Machine Translation (NMT) systems encounter a significant challenge when translating a pro-drop ('pronoun-dropping') language (e.g., Chinese) to a non-pro-drop one (e.g., English), since the pro-drop phenomenon demands NMT systems to recover omitted pronouns. This unique and crucial task, however, lacks sufficient datasets for benchmarking. To bridge this gap, we introduce PROSE, a new benchmark featured in diverse pro-drop instances for document-level Chinese-English spoken language translation. Furthermore, we conduct an in-depth investigation of the pro-drop phenomenon in spoken Chinese on this dataset, reconfirming that pro-drop reduces the performance of NMT systems in Chinese-English translation. To alleviate the negative impact introduced by pro-drop, we propose Mention-Aware Semantic Augmentation, a novel approach that leverages the semantic embedding of dropped pronouns to augment training pairs. Results from the experiments on four Chinese-English translation corpora show that our proposed method outperforms existing methods regarding omitted pronoun retrieval and overall translation quality.
Submission Number: 2355
Loading