activity
20152021
most citedNon-Autoregressive Neural Machine Translation

506 citations · 1.1k across the 24 of their papers we have counts for

collaborators

24 papers

cs.CL2021★ 3 cited

Show Me How To Revise: Improving Lexically Constrained Sentence Generation with XLNet

Xingwei He, Victor O. K. Li

Lexically constrained sentence generation allows the incorporation of prior knowledge such as lexical constraints into the output. This technique has been applied to machine transl…

cs.LG2021★ 1 cited

Deep-AIR: A Hybrid CNN-LSTM Framework for Air Quality Modeling in Metropolitan Cities

Yang Han, Qi Zhang, Victor O. K. Li +1

Air pollution has long been a serious environmental health challenge, especially in metropolitan cities, where air pollutant concentrations are exacerbated by the street canyon eff…

cs.HC2021★ 6 cited

AQEyes: Visual Analytics for Anomaly Detection and Examination of Air Quality Data

Dongyu Liu, Kalyan Veeramachaneni, Alexander Geiger +2

Anomaly detection plays a key role in air quality analysis by enhancing situational awareness and alerting users to potential hazards. However, existing anomaly detection approache…

cs.CL2020★ 1 cited

Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model

Juntao Li, Ruidan He, Hai Ye +3

Recent research indicates that pretraining cross-lingual language models on large-scale unlabeled texts yields significant performance improvements over various cross-lingual and l…

cs.CL2020

On the Sparsity of Neural Machine Translation Models

Yong Wang, Longyue Wang, Victor O. K. Li +1

Modern neural machine translation (NMT) models employ a large number of parameters, which leads to serious over-parameterization and typically causes the underutilization of comput…

cs.CV2020★ 2 cited

Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution

Yingruo Fan, Jacqueline C. K. Lam, Victor O. K. Li

The intensity estimation of facial action units (AUs) is challenging due to subtle changes in the person's facial appearance. Previous approaches mainly rely on probabilistic model…