activity
20172025
most citedNeural Machine Translation with Word Predictions

11 citations · 28 across the 9 of their papers we have counts for

collaborators

12 papers

cs.CL2025

Multilingual Non-Autoregressive Machine Translation without Knowledge Distillation

Chenyang Huang, Fei Huang, Zaixiang Zheng +3

Multilingual neural machine translation (MNMT) aims at using one single model for multiple translation directions. Recent work applies non-autoregressive Transformers to improve th…

cs.CL20221 cited

Helping the Weak Makes You Strong: Simple Multi-Task Learning Improves Non-Autoregressive Translators

Xinyou Wang, Zaixiang Zheng, Shujian Huang

Recently, non-autoregressive (NAR) neural machine translation models have received increasing attention due to their efficient parallel decoding. However, the probabilistic framewo…

cs.CL20216 cited

The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21

Lihua Qian, Yi Zhou, Zaixiang Zheng +7

This paper describes the Volctrans' submission to the WMT21 news translation shared task for German->English translation. We build a parallel (i.e., non-autoregressive) translation…

cs.CL20212 cited

DirectQE: Direct Pretraining for Machine Translation Quality Estimation

Qu Cui, Shujian Huang, Jiahuan Li +4

Machine Translation Quality Estimation (QE) is a task of predicting the quality of machine translations without relying on any reference. Recently, the predictor-estimator framewor…

cs.CL2020

RPD: A Distance Function Between Word Embeddings

Xuhui Zhou, Zaixiang Zheng, Shujian Huang

It is well-understood that different algorithms, training processes, and corpora produce different word embeddings. However, less is known about the relation between different embe…

cs.CL2020

Towards Making the Most of Context in Neural Machine Translation

Zaixiang Zheng, Xiang Yue, Shujian Huang +2

Document-level machine translation manages to outperform sentence level models by a small margin, but have failed to be widely adopted. We argue that previous research did not make…