activity
20192021
most citedUnified Mandarin TTS Front-end Based on Distilled BERT Model

15 citations · 30 across the 3 of their papers we have counts for

collaborators

6 papers

cs.CL202113 cited

Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger

Fanchao Qi, Mukai Li, Yangyi Chen +4

Backdoor attacks are a kind of insidious security threat against machine learning models. After being injected with a backdoor in training, the victim model will produce adversary-…

cs.SD202015 cited

Unified Mandarin TTS Front-end Based on Distilled BERT Model

Yang Zhang, Liqun Deng, Yasheng Wang

The front-end module in a typical Mandarin text-to-speech system (TTS) is composed of a long pipeline of text processing components, which requires extensive efforts to build and i…

cs.CL2020

Better Robustness by More Coverage: Adversarial Training with Mixup Augmentation for Robust Fine-tuning

Chenglei Si, Zhengyan Zhang, Fanchao Qi +4

Pretrained language models (PLMs) perform poorly under adversarial attacks. To improve the adversarial robustness, adversarial data augmentation (ADA) has been widely adopted to co…

cs.CL20192 cited

Multi-channel Reverse Dictionary Model

Lei Zhang, Fanchao Qi, Zhiyuan Liu +3

A reverse dictionary takes the description of a target word as input and outputs the target word together with other words that match the description. Existing reverse dictionary m…

cs.CL2019

Improving Sequence Modeling Ability of Recurrent Neural Networks via Sememes

Yujia Qin, Fanchao Qi, Sicong Ouyang +5

Sememes, the minimum semantic units of human languages, have been successfully utilized in various natural language processing applications. However, most existing studies exploit…

cs.CL2019

GPT-based Generation for Classical Chinese Poetry

Yi Liao, Yasheng Wang, Qun Liu +1

We present a simple yet effective method for generating high quality classical Chinese poetry with Generative Pre-trained Language Model (GPT). The method adopts a simple GPT model…