138 citations · 191 across the 15 of their papers we have counts for
15 papers
BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Training
Yiming Yan, Tao Wang, Chengqi Zhao +3
Automatic metrics play a crucial role in machine translation. Despite the widespread use of n-gram-based metrics, there has been a recent surge in the development of pre-trained mo…
Recent Advances in Direct Speech-to-text Translation
Chen Xu, Rong Ye, Qianqian Dong +5
Recently, speech-to-text translation has attracted more and more attention and many studies have emerged rapidly. In this paper, we present a comprehensive survey on direct speech…
Improving speech translation by fusing speech and text
Wenbiao Yin, Zhicheng Liu, Chengqi Zhao +3
In speech translation, leveraging multimodal data to improve model performance and address limitations of individual modalities has shown significant effectiveness. In this paper,…
Selective Knowledge Distillation for Non-Autoregressive Neural Machine Translation
Min Liu, Yu Bao, Chengqi Zhao +1
Benefiting from the sequence-level knowledge distillation, the Non-Autoregressive Transformer (NAT) achieves great success in neural machine translation tasks. However, existing kn…
WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research
Xinhao Mei, Chutong Meng, Haohe Liu +6
The advancement of audio-language (AL) multimodal learning tasks has been significant in recent years. However, researchers face challenges due to the costly and time-consuming col…
GigaST: A 10,000-hour Pseudo Speech Translation Corpus
Rong Ye, Chengqi Zhao, Tom Ko +4
This paper introduces GigaST, a large-scale pseudo speech translation (ST) corpus. We create the corpus by translating the text in GigaSpeech, an English ASR corpus, into German an…
Secoco: Self-Correcting Encoding for Neural Machine Translation
Tao Wang, Chengqi Zhao, Mingxuan Wang +3
This paper presents Self-correcting Encoding (Secoco), a framework that effectively deals with input noise for robust neural machine translation by introducing self-correcting pred…
The Volctrans Neural Speech Translation System for IWSLT 2021
Chengqi Zhao, Zhicheng Liu, Jian Tong +6
This paper describes the systems submitted to IWSLT 2021 by the Volctrans team. We participate in the offline speech translation and text-to-text simultaneous translation tracks. F…
Autocorrect in the Process of Translation -- Multi-task Learning Improves Dialogue Machine Translation
Tao Wang, Chengqi Zhao, Mingxuan Wang +2
Automatic translation of dialogue texts is a much needed demand in many real life scenarios. However, the currently existing neural machine translation delivers unsatisfying result…
Counter-Interference Adapter for Multilingual Machine Translation
Yaoming Zhu, Jiangtao Feng, Chengqi Zhao +2
Developing a unified multilingual model has long been a pursuit for machine translation. However, existing approaches suffer from performance degradation -- a single multilingual m…
Finding Sparse Structures for Domain Specific Neural Machine Translation
Jianze Liang, Chengqi Zhao, Mingxuan Wang +2
Neural machine translation often adopts the fine-tuning approach to adapt to specific domains. However, nonrestricted fine-tuning can easily degrade on the general domain and over-…
NeurST: Neural Speech Translation Toolkit
Chengqi Zhao, Mingxuan Wang, Qianqian Dong +2
NeurST is an open-source toolkit for neural speech translation. The toolkit mainly focuses on end-to-end speech translation, which is easy to use, modify, and extend to advanced sp…
Rethinking Document-level Neural Machine Translation
Zewei Sun, Mingxuan Wang, Hao Zhou +4
This paper does not aim at introducing a novel model for document-level neural machine translation. Instead, we head back to the original Transformer model and hope to answer the f…
Kernelized Bayesian Softmax for Text Generation
Ning Miao, Hao Zhou, Chengqi Zhao +2
Neural models for text generation require a softmax layer with proper token embeddings during the decoding phase. Most existing approaches adopt single point embedding for each tok…
Towards Making the Most of BERT in Neural Machine Translation
Jiacheng Yang, Mingxuan Wang, Hao Zhou +4
GPT-2 and BERT demonstrate the effectiveness of using pre-trained language models (LMs) on various natural language processing tasks. However, LM fine-tuning often suffers from cat…