Representation Degeneration Problem in Training Natural Language Generation Models

Jun Gao, Di He, Xu Tan +3

Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter

Lijun Wu, Xu Tan, Di He +4

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

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

The paper introduces a token‑level ensemble distillation method using Transformers to improve grapheme‑to‑phoneme conversion accuracy and reduce model size, leveraging unlabeled da…

Unsupervised Pivot Translation for Distant Languages

Yichong Leng, Xu Tan, Tao Qin +2

Sentence-wise Smooth Regularization for Sequence to Sequence Learning

Chengyue Gong, Xu Tan, Di He +1

Hybrid Self-Attention Network for Machine Translation

Kaitao Song, Xu Tan, Furong Peng +1

Dense Information Flow for Neural Machine Translation

Yanyao Shen, Xu Tan, Di He +2

MASS: Masked Sequence to Sequence Pre-training for Language Generation

Kaitao Song, Xu Tan, Tao Qin +2

Double Path Networks for Sequence to Sequence Learning

Kaitao Song, Xu Tan, Di He +3

Achieving Human Parity on Automatic Chinese to English News Translation

Hany Hassan, Anthony Aue, Chang Chen +21

Multilingual Neural Machine Translation with Knowledge Distillation

Xu Tan, Yi Ren, Di He +3

Non-Autoregressive Neural Machine Translation with Enhanced Decoder Input

Junliang Guo, Xu Tan, Di He +3