67 citations · 245 across the 29 of their papers we have counts for
5 papers · 1 filter
Mitigating Negative Style Transfer in Hybrid Dialogue System
Shimin Li, Qinyuan Cheng, Linyang Li +1
As the functionality of dialogue systems evolves, hybrid dialogue systems that accomplish user-specific goals and participate in open-topic chitchat with users are attracting growi…
Is MultiWOZ a Solved Task? An Interactive TOD Evaluation Framework with User Simulator
Qinyuan Cheng, Linyang Li, Guofeng Quan +3
Task-Oriented Dialogue (TOD) systems are drawing more and more attention in recent studies. Current methods focus on constructing pre-trained models or fine-tuning strategies while…
"Is Whole Word Masking Always Better for Chinese BERT?": Probing on Chinese Grammatical Error Correction
Yong Dai, Linyang Li, Cong Zhou +5
Whole word masking (WWM), which masks all subwords corresponding to a word at once, makes a better English BERT model. For the Chinese language, however, there is no subword becaus…
Text Adversarial Purification as Defense against Adversarial Attacks
Linyang Li, Demin Song, Xipeng Qiu
Adversarial purification is a successful defense mechanism against adversarial attacks without requiring knowledge of the form of the incoming attack. Generally, adversarial purifi…
MarkBERT: Marking Word Boundaries Improves Chinese BERT
Linyang Li, Yong Dai, Duyu Tang +3
We present a Chinese BERT model dubbed MarkBERT that uses word information in this work. Existing word-based BERT models regard words as basic units, however, due to the vocabulary…