6 papers · 1 filter
An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation
Pengzhi Gao, Ruiqing Zhang, Zhongjun He +2
Consistency regularization methods, such as R-Drop (Liang et al., 2021) and CrossConST (Gao et al., 2023), have achieved impressive supervised and zero-shot performance in the neur…
Learning Multilingual Sentence Representations with Cross-lingual Consistency Regularization
Pengzhi Gao, Liwen Zhang, Zhongjun He +2
Multilingual sentence representations are the foundation for similarity-based bitext mining, which is crucial for scaling multilingual neural machine translation (NMT) system to mo…
Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization
Pengzhi Gao, Liwen Zhang, Zhongjun He +2
The multilingual neural machine translation (NMT) model has a promising capability of zero-shot translation, where it could directly translate between language pairs unseen during…
Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation
Pengzhi Gao, Zhongjun He, Hua Wu +1
We introduce Bi-SimCut: a simple but effective training strategy to boost neural machine translation (NMT) performance. It consists of two procedures: bidirectional pretraining and…
Mixup Decoding for Diverse Machine Translation
Jicheng Li, Pengzhi Gao, Xuanfu Wu +4
Diverse machine translation aims at generating various target language translations for a given source language sentence. Leveraging the linear relationship in the sentence latent…
A Data-Centric Framework for Composable NLP Workflows
Zhengzhong Liu, Guanxiong Ding, Avinash Bukkittu +15
Empirical natural language processing (NLP) systems in application domains (e.g., healthcare, finance, education) involve interoperation among multiple components, ranging from dat…