activity
20192021
most citedPrevent the Language Model from being Overconfident in Neural Machine Translation

5 citations · 8 across the 5 of their papers we have counts for

collaborators

10 papers

cs.CL2025

Warmup-Distill: Bridge the Distribution Mismatch between Teacher and Student before Knowledge Distillation

Zengkui Sun, Yijin Liu, Fandong Meng +3

The widespread deployment of Large Language Models (LLMs) is hindered by the high computational demands, making knowledge distillation (KD) crucial for developing compact smaller o…

cs.CL2025

Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical Mapping

Yijie Chen, Yijin Liu, Fandong Meng +3

Knowledge Distillation (KD) has emerged as a prominent technique for model compression. However, conventional KD approaches primarily focus on homogeneous architectures with identi…

cs.CL2021

Scheduled Sampling Based on Decoding Steps for Neural Machine Translation

Yijin Liu, Fandong Meng, Yufeng Chen +2

Scheduled sampling is widely used to mitigate the exposure bias problem for neural machine translation. Its core motivation is to simulate the inference scene during training by re…

cs.CL2021

Confidence-Aware Scheduled Sampling for Neural Machine Translation

Yijin Liu, Fandong Meng, Yufeng Chen +2

Scheduled sampling is an effective method to alleviate the exposure bias problem of neural machine translation. It simulates the inference scene by randomly replacing ground-truth…

cs.CL20215 cited

Prevent the Language Model from being Overconfident in Neural Machine Translation

Mengqi Miao, Fandong Meng, Yijin Liu +2

The Neural Machine Translation (NMT) model is essentially a joint language model conditioned on both the source sentence and partial translation. Therefore, the NMT model naturally…

cs.CL20212 cited

Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation

Yangyifan Xu, Yijin Liu, Fandong Meng +3

Recently, token-level adaptive training has achieved promising improvement in machine translation, where the cross-entropy loss function is adjusted by assigning different training…