activity
20192022
most citedCoLAKE: Contextualized Language and Knowledge Embedding

20 citations · 88 across the 10 of their papers we have counts for

collaborators

10 papers

cs.CL202213 cited

DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models

Zhengfu He, Tianxiang Sun, Kuanning Wang +2

We present DiffusionBERT, a new generative masked language model based on discrete diffusion models. Diffusion models and many pre-trained language models have a shared training ob…

cs.CL2022

Late Prompt Tuning: A Late Prompt Could Be Better Than Many Prompts

Xiangyang Liu, Tianxiang Sun, Xuanjing Huang +1

Prompt tuning is a parameter-efficient tuning (PETuning) method for utilizing pre-trained models (PTMs) that simply prepends a soft prompt to the input and only optimizes the promp…

cs.CL20222 cited

BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation

Tianxiang Sun, Junliang He, Xipeng Qiu +1

Automatic evaluation metrics are crucial to the development of generative systems. In recent years, pre-trained language model (PLM) based metrics, such as BERTScore, have been com…

cs.CL2022

A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation

Tianxiang Sun, Xiangyang Liu, Wei Zhu +7

Early exiting allows instances to exit at different layers according to the estimation of difficulty. Previous works usually adopt heuristic metrics such as the entropy of internal…

cs.LG20216 cited

Learning to Teach with Student Feedback

Yitao Liu, Tianxiang Sun, Xipeng Qiu +1

Knowledge distillation (KD) has gained much attention due to its effectiveness in compressing large-scale pre-trained models. In typical KD methods, the small student model is trai…

cs.CL20214 cited

Accelerating BERT Inference for Sequence Labeling via Early-Exit

Xiaonan Li, Yunfan Shao, Tianxiang Sun +3

Both performance and efficiency are crucial factors for sequence labeling tasks in many real-world scenarios. Although the pre-trained models (PTMs) have significantly improved the…