b'Mingxuan Wang'

research

∙ 07/06/2023

BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Training

Automatic metrics play a crucial role in machine translation. Despite th...

0 Yiming Yan, et al. ∙

research

∙ 06/18/2023

MOSPC: MOS Prediction Based on Pairwise Comparison

As a subjective metric to evaluate the quality of synthesized speech, Me...

0 Kexin Wang, et al. ∙

research

∙ 06/15/2023

Understanding Parameter Sharing in Transformers

Parameter sharing has proven to be a parameter-efficient approach. Previ...

0 Ye Lin, et al. ∙

research

∙ 06/07/2023

MobileNMT: Enabling Translation in 15MB and 30ms

Deploying NMT models on mobile devices is essential for privacy, low lat...

0 Ye Lin, et al. ∙

research

∙ 05/19/2023

DUB: Discrete Unit Back-translation for Speech Translation

How can speech-to-text translation (ST) perform as well as machine trans...

0 Dong Zhang, et al. ∙

research

∙ 02/20/2023

DINOISER: Diffused Conditional Sequence Learning by Manipulating Noises

While diffusion models have achieved great success in generating continu...

0 Jiasheng Ye, et al. ∙

research

∙ 12/20/2022

Beyond Triplet: Leveraging the Most Data for Multimodal Machine Translation

Multimodal machine translation (MMT) aims to improve translation quality...

0 Yaoming Zhu, et al. ∙

research

∙ 12/19/2022

SEScore2: Retrieval Augmented Pretraining for Text Generation Evaluation

Is it possible to leverage large scale raw and raw parallel corpora to b...

0 Wenda Xu, et al. ∙

research

∙ 12/17/2022

Better Datastore, Better Translation: Generating Datastores from Pre-Trained Models for Nearest Neural Machine Translation

Nearest Neighbor Machine Translation (kNNMT) is a simple and effective m...

0 Jiahuan Li, et al. ∙

research

∙ 12/07/2022

M3ST: Mix at Three Levels for Speech Translation

How to solve the data scarcity problem for end-to-end speech-to-text tra...

0 Xuxin Cheng, et al. ∙

research

∙ 10/20/2022

The VolcTrans System for WMT22 Multilingual Machine Translation Task

This report describes our VolcTrans system for the WMT22 shared task on ...

0 Xian Qian, et al. ∙

research

∙ 10/08/2022

CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning

Speech is the surface form of a finite set of phonetic units, which can ...

0 Chutong Meng, et al. ∙

research

∙ 09/23/2022

Zero-shot Domain Adaptation for Neural Machine Translation with Retrieved Phrase-level Prompts

Domain adaptation is an important challenge for neural machine translati...

0 Zewei Sun, et al. ∙

research

∙ 05/18/2022

Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation

Direct Speech-to-speech translation (S2ST) has drawn more and more atten...

0 Qianqian Dong, et al. ∙

research

∙ 05/05/2022

Cross-modal Contrastive Learning for Speech Translation

How can we learn unified representations for spoken utterances and their...

0 Rong Ye, et al. ∙

research

∙ 04/08/2022

GigaST: A 10,000-hour Pseudo Speech Translation Corpus

This paper introduces GigaST, a large-scale pseudo speech translation (S...

0 Rong Ye, et al. ∙

research

∙ 03/20/2022

STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation

How to learn a better speech representation for end-to-end speech-to-tex...

0 Qingkai Fang, et al. ∙

research

∙ 01/24/2022

Unified Multimodal Punctuation Restoration Framework for Mixed-Modality Corpus

The punctuation restoration task aims to correctly punctuate the output ...

0 Yaoming Zhu, et al. ∙

research

∙ 10/12/2021

LightSeq2: Accelerated Training for Transformer-based Models on GPUs

Transformer-based neural models are used in many AI applications. Traini...

5 Xiaohui Wang, et al. ∙

research

∙ 09/23/2021

The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21

This paper describes the Volctrans' submission to the WMT21 news transla...

0 Lihua Qian, et al. ∙

research

∙ 09/21/2021

Learning Kernel-Smoothed Machine Translation with Retrieved Examples

How to effectively adapt neural machine translation (NMT) models accordi...

0 Qingnan Jiang, et al. ∙

research

∙ 09/15/2021

UniST: Unified End-to-end Model for Streaming and Non-streaming Speech Translation

This paper presents a unified end-to-end frame-work for both streaming a...

0 Qianqian Dong, et al. ∙

research

∙ 09/11/2021

Multilingual Translation via Grafting Pre-trained Language Models

Can pre-trained BERT for one language and GPT for another be glued toget...

0 Zewei Sun, et al. ∙

research

∙ 08/27/2021

Secoco: Self-Correcting Encoding for Neural Machine Translation

This paper presents Self-correcting Encoding (Secoco), a framework that ...

4 PetsTime, et al. ∙

research

∙ 06/15/2021

Language Tags Matter for Zero-Shot Neural Machine Translation

Multilingual Neural Machine Translation (MNMT) has aroused widespread in...

0 Liwei Wu, et al. ∙

research

∙ 05/20/2021

Contrastive Learning for Many-to-many Multilingual Neural Machine Translation

Existing multilingual machine translation approaches mainly focus on Eng...

0 Xiao Pan, et al. ∙

research

∙ 05/19/2021

Learning Language Specific Sub-network for Multilingual Machine Translation

Multilingual neural machine translation aims at learning a single transl...

0 Zehui Lin, et al. ∙

research

∙ 05/16/2021

The Volctrans Neural Speech Translation System for IWSLT 2021

This paper describes the systems submitted to IWSLT 2021 by the Volctran...

7 Chengqi Zhao, et al. ∙

research

∙ 05/07/2021

Learning Shared Semantic Space for Speech-to-Text Translation

Having numerous potential applications and great impact, end-to-end spee...

0 Chi Han, et al. ∙

research

∙ 04/21/2021

End-to-end Speech Translation via Cross-modal Progressive Training

End-to-end speech translation models have become a new trend in the rese...

0 Rong Ye, et al. ∙

research

∙ 04/16/2021

Serial or Parallel? Plug-able Adapter for multilingual machine translation

Developing a unified multilingual translation model is a key topic in ma...

0 Yaoming Zhu, et al. ∙

research

∙ 03/30/2021

Auto Correcting in the Process of Translation – Multi-task Learning Improves Dialogue Machine Translation

Automatic translation of dialogue texts is a much needed demand in many ...

5 PetsTime, et al. ∙

research

∙ 12/19/2020

Finding Sparse Structure for Domain Specific Neural Machine Translation

Fine-tuning is a major approach for domain adaptation in Neural Machine ...

0 Jianze Liang, et al. ∙

research

∙ 12/18/2020

NeurST: Neural Speech Translation Toolkit

NeurST is an open-source toolkit for neural speech translation developed...

0 Chengqi Zhao, et al. ∙

research

∙ 12/05/2020

Reciprocal Supervised Learning Improves Neural Machine Translation

Despite the recent success on image classification, self-training has on...

0 Minkai Xu, et al. ∙

research

∙ 11/02/2020

On the Sentence Embeddings from Pre-trained Language Models

Pre-trained contextual representations like BERT have achieved great suc...

0 Bohan Li, et al. ∙

research

∙ 10/28/2020

The Volctrans Machine Translation System for WMT20

This paper describes our VolcTrans system on WMT20 shared news translati...

0 Liwei Wu, et al. ∙

research

∙ 10/27/2020

Volctrans Parallel Corpus Filtering System for WMT 2020

In this paper, we describe our submissions to the WMT20 shared task on p...

0 Runxin Xu, et al. ∙

research

∙ 10/23/2020

LightSeq: A High Performance Inference Library for Transformers

Transformer, BERT and their variants have achieved great success in natu...

13 Xiaohui Wang, et al. ∙

research

∙ 10/18/2020

Capturing Longer Context for Document-level Neural Machine Translation: A Multi-resolutional Approach

Discourse context has been proven useful when translating documents. It ...

0 Zewei Sun, et al. ∙

research

∙ 10/07/2020

Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information

We investigate the following question for machine translation (MT): can ...

0 Zehui Lin, et al. ∙

research

∙ 09/21/2020

SDST: Successive Decoding for Speech-to-text Translation

End-to-end speech-to-text translation (ST), which directly translates th...

0 Qianqian Dong, et al. ∙

research

∙ 09/21/2020

TED: Triple Supervision Decouples End-to-end Speech-to-text Translation

An end-to-end speech-to-text translation (ST) takes audio in a source la...

0 Qianqian Dong, et al. ∙

research

∙ 09/21/2020

Generative Imagination Elevates Machine Translation

There are thousands of languages on earth, but visual perception is shar...

7 Quanyu Long, et al. ∙

research

∙ 08/18/2020

Glancing Transformer for Non-Autoregressive Neural Machine Translation

Non-autoregressive neural machine translation achieves remarkable infere...

0 Lihua Qian, et al. ∙

research

∙ 07/12/2020

Improving Maximum Likelihood Training for Text Generation with Density Ratio Estimation

Auto-regressive sequence generative models trained by Maximum Likelihood...

4 Yuxuan Song, et al. ∙

research

∙ 07/12/2020

Xiaomingbot: A Multilingual Robot News Reporter

This paper proposes the building of Xiaomingbot, an intelligent, multili...

0 Runxin Xu, et al. ∙

research

∙ 04/07/2020

Unsupervised Neural Machine Translation with Indirect Supervision

Neural machine translation (NMT) is ineffective for zero-resource langua...

0 Hongxiao Bai, et al. ∙

research

∙ 11/25/2019

Non-autoregressive Transformer by Position Learning

Non-autoregressive models are promising on various text generation tasks...

0 Yu Bao, et al. ∙

research

∙ 08/15/2019

Towards Making the Most of BERT in Neural Machine Translation

GPT-2 and BERT demonstrate the effectiveness of using pre-trained langua...

0 Jiacheng Yang, et al. ∙

Mingxuan Wang

Featured Co-authors