activity
20172023
most citedMinimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine Translation

41 citations · 151 across the 22 of their papers we have counts for

collaborators
Showing 2020Show all

8 papers · 1 filter

cs.CL2020★ 2 cited

Future-Guided Incremental Transformer for Simultaneous Translation

Shaolei Zhang, Yang Feng, Liangyou Li

Simultaneous translation (ST) starts translations synchronously while reading source sentences, and is used in many online scenarios. The previous wait-k policy is concise and achi…

cs.CL2020★ 1 cited

Investigating Catastrophic Forgetting During Continual Training for Neural Machine Translation

Shuhao Gu, Yang Feng

Neural machine translation (NMT) models usually suffer from catastrophic forgetting during continual training where the models tend to gradually forget previously learned knowledge…

cs.CL2020

Generating Diverse Translation from Model Distribution with Dropout

Xuanfu Wu, Yang Feng, Chenze Shao

Despite the improvement of translation quality, neural machine translation (NMT) often suffers from the lack of diversity in its generation. In this paper, we propose to generate d…

cs.CL2020

Token-level Adaptive Training for Neural Machine Translation

Shuhao Gu, Jinchao Zhang, Fandong Meng +4

There exists a token imbalance phenomenon in natural language as different tokens appear with different frequencies, which leads to different learning difficulties for tokens in Ne…

cs.CL2020★ 12 cited

CDL: Curriculum Dual Learning for Emotion-Controllable Response Generation

Lei Shen, Yang Feng

Emotion-controllable response generation is an attractive and valuable task that aims to make open-domain conversations more empathetic and engaging. Existing methods mainly enhanc…

cs.CL2020

A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking

Yong Shan, Zekang Li, Jinchao Zhang +4

Recent studies in dialogue state tracking (DST) leverage historical information to determine states which are generally represented as slot-value pairs. However, most of them have…