activity
20182023
most citedNon-Autoregressive Neural Machine Translation with Enhanced Decoder Input

16 citations · 44 across the 7 of their papers we have counts for

collaborators
Showing cs.CLShow all

10 papers · 1 filter

cs.CL2023★ 1 cited

TranSFormer: Slow-Fast Transformer for Machine Translation

Bei Li, Yi Jing, Xu Tan +3

Learning multiscale Transformer models has been evidenced as a viable approach to augmenting machine translation systems. Prior research has primarily focused on treating subwords…

cs.CL2020★ 9 cited

LightPAFF: A Two-Stage Distillation Framework for Pre-training and Fine-tuning

Kaitao Song, Hao Sun, Xu Tan +4

While pre-training and fine-tuning, e.g., BERT~\citep{devlin2018bert}, GPT-2~\citep{radford2019language}, have achieved great success in language understanding and generation tasks…

cs.CL2020

MPNet: Masked and Permuted Pre-training for Language Understanding

Kaitao Song, Xu Tan, Tao Qin +2

BERT adopts masked language modeling (MLM) for pre-training and is one of the most successful pre-training models. Since BERT neglects dependency among predicted tokens, XLNet intr…

cs.CL2019

Representation Degeneration Problem in Training Natural Language Generation Models

Jun Gao, Di He, Xu Tan +3

We study an interesting problem in training neural network-based models for natural language generation tasks, which we call the \emph{representation degeneration problem}. We obse…

cs.CL2019

Token-Level Ensemble Distillation for Grapheme-to-Phoneme Conversion

Hao Sun, Xu Tan, Jun-Wei Gan +4

Grapheme-to-phoneme (G2P) conversion is an important task in automatic speech recognition and text-to-speech systems. Recently, G2P conversion is viewed as a sequence to sequence t…

cs.CL2018★ 16 cited

Non-Autoregressive Neural Machine Translation with Enhanced Decoder Input

Junliang Guo, Xu Tan, Di He +3

Non-autoregressive translation (NAT) models, which remove the dependence on previous target tokens from the inputs of the decoder, achieve significantly inference speedup but at th…