activity
20202022
most citedEnhancing Content Preservation in Text Style Transfer Using Reverse Attention and Conditional Layer Normalization

2 citations · 4 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CL20221 cited

Semi-Supervised Lifelong Language Learning

Yingxiu Zhao, Yinhe Zheng, Bowen Yu +6

Lifelong learning aims to accumulate knowledge and alleviate catastrophic forgetting when learning tasks sequentially. However, existing lifelong language learning methods only foc…

cs.LG20221 cited

Adaptive Label Smoothing with Self-Knowledge in Natural Language Generation

Dongkyu Lee, Ka Chun Cheung, Nevin L. Zhang

Overconfidence has been shown to impair generalization and calibration of a neural network. Previous studies remedy this issue by adding a regularization term to a loss function, p…

cs.CL2022

Hard Gate Knowledge Distillation -- Leverage Calibration for Robust and Reliable Language Model

Dongkyu Lee, Zhiliang Tian, Yingxiu Zhao +2

In knowledge distillation, a student model is trained with supervisions from both knowledge from a teacher and observations drawn from a training data distribution. Knowledge of a…

cs.CL20212 cited

Enhancing Content Preservation in Text Style Transfer Using Reverse Attention and Conditional Layer Normalization

Dongkyu Lee, Zhiliang Tian, Lanqing Xue +1

Text style transfer aims to alter the style (e.g., sentiment) of a sentence while preserving its content. A common approach is to map a given sentence to content representation tha…

cs.CL2021

Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks

Zhiliang Tian, Wei Bi, Zihan Zhang +3

Personalized conversation models (PCMs) generate responses according to speaker preferences. Existing personalized conversation tasks typically require models to extract speaker pr…

cs.CL2020

Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation

Zhiliang Tian, Wei Bi, Dongkyu Lee +4

Neural conversation models are known to generate appropriate but non-informative responses in general. A scenario where informativeness can be significantly enhanced is Conversing…