activity
20152022
most citedNeural Rating Regression with Abstractive Tips Generation for Recommendation

306 citations · 500 across the 24 of their papers we have counts for

collaborators
Showing cs.CLShow all

34 papers · 1 filter

cs.CL2022

A Survey on Backdoor Attack and Defense in Natural Language Processing

Xuan Sheng, Zhaoyang Han, Piji Li +1

Deep learning is becoming increasingly popular in real-life applications, especially in natural language processing (NLP). Users often choose training outsourcing or adopt third-pa…

cs.CL20221 cited

uChecker: Masked Pretrained Language Models as Unsupervised Chinese Spelling Checkers

Piji Li

The task of Chinese Spelling Check (CSC) is aiming to detect and correct spelling errors that can be found in the text. While manually annotating a high-quality dataset is expensiv…

cs.CL2022

PromptAttack: Prompt-based Attack for Language Models via Gradient Search

Yundi Shi, Piji Li, Changchun Yin +3

As the pre-trained language models (PLMs) continue to grow, so do the hardware and data requirements for fine-tuning PLMs. Therefore, the researchers have come up with a lighter me…

cs.CL20221 cited

Parameter-Efficient Tuning by Manipulating Hidden States of Pretrained Language Models For Classification Tasks

Haoran Yang, Piji Li, Wai Lam

Parameter-efficient tuning aims to distill knowledge for downstream tasks by optimizing a few introduced parameters while freezing the pretrained language models (PLMs). Continuous…

cs.CL20212 cited

Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction

Piji Li, Shuming Shi

We investigate the problem of Chinese Grammatical Error Correction (CGEC) and present a new framework named Tail-to-Tail (\textbf{TtT}) non-autoregressive sequence prediction to ad…

cs.CL202110 cited

Non-Autoregressive Text Generation with Pre-trained Language Models

Yixuan Su, Deng Cai, Yan Wang +4

Non-autoregressive generation (NAG) has recently attracted great attention due to its fast inference speed. However, the generation quality of existing NAG models still lags behind…