activity
20182022
most citedDefending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrifice

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

collaborators

7 papers

cs.LG2022

Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language Model

Jiayi Wang, Rongzhou Bao, Zhuosheng Zhang +1

Recently, the problem of robustness of pre-trained language models (PrLMs) has received increasing research interest. Latest studies on adversarial attacks achieve high attack succ…

cs.CL2021

Beyond Glass-Box Features: Uncertainty Quantification Enhanced Quality Estimation for Neural Machine Translation

Ke Wang, Yangbin Shi, Jiayi Wang +3

Quality Estimation (QE) plays an essential role in applications of Machine Translation (MT). Traditionally, a QE system accepts the original source text and translation from a blac…

cs.CL20214 cited

Defending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrifice

Rongzhou Bao, Jiayi Wang, Hai Zhao

Pre-trained contextualized language models (PrLMs) have led to strong performance gains in downstream natural language understanding tasks. However, PrLMs can still be easily foole…

cs.CL20201 cited

Enhancing Pre-trained Language Model with Lexical Simplification

Rongzhou Bao, Jiayi Wang, Zhuosheng Zhang +1

For both human readers and pre-trained language models (PrLMs), lexical diversity may lead to confusion and inaccuracy when understanding the underlying semantic meanings of given…

cs.CL20203 cited

Computer Assisted Translation with Neural Quality Estimation and Automatic Post-Editing

Jiayi Wang, Ke Wang, Niyu Ge +3

With the advent of neural machine translation, there has been a marked shift towards leveraging and consuming the machine translation results. However, the gap between machine tran…

cs.CL2019

Neural Zero-Inflated Quality Estimation Model For Automatic Speech Recognition System

Kai Fan, Jiayi Wang, Bo Li +4

The performances of automatic speech recognition (ASR) systems are usually evaluated by the metric word error rate (WER) when the manually transcribed data are provided, which are,…