no code implementations • 6 Jul 2023 • Yiming Yan, Tao Wang, Chengqi Zhao, ShuJian Huang, Jiajun Chen, Mingxuan Wang
In this study, we systematically analyze and compare various mainstream and cutting-edge automatic metrics from the perspective of their guidance for training machine translation systems.
no code implementations • 20 Jun 2023 • Chen Xu, Rong Ye, Qianqian Dong, Chengqi Zhao, Tom Ko, Mingxuan Wang, Tong Xiao, Jingbo Zhu
Recently, speech-to-text translation has attracted more and more attention and many studies have emerged rapidly.
no code implementations • 23 May 2023 • Wenbiao Yin, Zhicheng Liu, Chengqi Zhao, Tao Wang, Jian Tong, Rong Ye
To tackle these gaps, we propose \textbf{F}use-\textbf{S}peech-\textbf{T}ext (\textbf{FST}), a cross-modal model which supports three distinct input modalities for translation: speech, text, and fused speech-text.
no code implementations • 31 Mar 2023 • Min Liu, Yu Bao, Chengqi Zhao, ShuJian Huang
Benefiting from the sequence-level knowledge distillation, the Non-Autoregressive Transformer (NAT) achieves great success in neural machine translation tasks.
3 code implementations • 30 Mar 2023 • Xinhao Mei, Chutong Meng, Haohe Liu, Qiuqiang Kong, Tom Ko, Chengqi Zhao, Mark D. Plumbley, Yuexian Zou, Wenwu Wang
To address this data scarcity issue, we introduce WavCaps, the first large-scale weakly-labelled audio captioning dataset, comprising approximately 400k audio clips with paired captions.
Ranked #1 on Zero-Shot Environment Sound Classification on ESC-50 (using extra training data)
1 code implementation • 8 Apr 2022 • Rong Ye, Chengqi Zhao, Tom Ko, Chutong Meng, Tao Wang, Mingxuan Wang, Jun Cao
The training set is translated by a strong machine translation system and the test set is translated by human.
no code implementations • Findings (EMNLP) 2021 • Tao Wang, Chengqi Zhao, Mingxuan Wang, Lei LI, Hang Li, Deyi Xiong
This paper presents Self-correcting Encoding (Secoco), a framework that effectively deals with input noise for robust neural machine translation by introducing self-correcting predictors.
no code implementations • NAACL 2021 • Tao Wang, Chengqi Zhao, Mingxuan Wang, Lei LI, Deyi Xiong
Automatic translation of dialogue texts is a much needed demand in many real life scenarios.
1 code implementation • ACL (IWSLT) 2021 • Chengqi Zhao, Zhicheng Liu, Jian Tong, Tao Wang, Mingxuan Wang, Rong Ye, Qianqian Dong, Jun Cao, Lei LI
For offline speech translation, our best end-to-end model achieves 8. 1 BLEU improvements over the benchmark on the MuST-C test set and is even approaching the results of a strong cascade solution.
1 code implementation • Findings (EMNLP) 2021 • Yaoming Zhu, Jiangtao Feng, Chengqi Zhao, Mingxuan Wang, Lei LI
Developing a unified multilingual model has long been a pursuit for machine translation.
1 code implementation • 30 Mar 2021 • Tao Wang, Chengqi Zhao, Mingxuan Wang, Lei LI, Deyi Xiong
Automatic translation of dialogue texts is a much needed demand in many real life scenarios.
2 code implementations • 19 Dec 2020 • Jianze Liang, Chengqi Zhao, Mingxuan Wang, Xipeng Qiu, Lei LI
Neural machine translation often adopts the fine-tuning approach to adapt to specific domains.
1 code implementation • ACL 2021 • Chengqi Zhao, Mingxuan Wang, Qianqian Dong, Rong Ye, Lei LI
NeurST is an open-source toolkit for neural speech translation.
Ranked #1 on Speech-to-Text Translation on libri-trans
1 code implementation • Findings (ACL) 2022 • Zewei Sun, Mingxuan Wang, Hao Zhou, Chengqi Zhao, ShuJian Huang, Jiajun Chen, Lei LI
This paper does not aim at introducing a novel model for document-level neural machine translation.
1 code implementation • NeurIPS 2019 • Ning Miao, Hao Zhou, Chengqi Zhao, Wenxian Shi, Lei LI
Neural models for text generation require a softmax layer with proper token embeddings during the decoding phase.
2 code implementations • 15 Aug 2019 • Jiacheng Yang, Mingxuan Wang, Hao Zhou, Chengqi Zhao, Yong Yu, Wei-Nan Zhang, Lei LI
Our experiments in machine translation show CTNMT gains of up to 3 BLEU score on the WMT14 English-German language pair which even surpasses the previous state-of-the-art pre-training aided NMT by 1. 4 BLEU score.