Cao Liu

Cao Liu

Auto-generated profile, based on publicly available information

Cao Liu

Meituan

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2023
Verified
Conference Paper
Open access
PDF file
ZYZhao Yang
Zhao Yang
YZYuanzhe Zhang
Yuanzhe Zhang
DSDianbo Sui
Dianbo Sui
CLCao Liu
Cao Liu
JZJun Zhao
Jun Zhao
KLKang Liu
Kang Liu
Zhao Yang, Yuanzhe Zhang, Dianbo Sui, Cao Liu, Jun Zhao, Kang Liu. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

1 January 2023
Verified
Conference Paper
Open access
PDF file
ZJZhongtao Jiang
Zhongtao Jiang
YZYuanzhe Zhang
Yuanzhe Zhang
CLCao Liu
Cao Liu
JZJun Zhao
Jun Zhao
KLKang Liu
Kang Liu
Zhongtao Jiang, Yuanzhe Zhang, Cao Liu, Jun Zhao, Kang Liu. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.

9 October 2024 in ACM Transactions on Knowledge Discovery From Data
Verified
Journal Article
Open access
JYJiacheng Yang
Jiacheng Yang
MCMiaoxin Chen
Miaoxin Chen
CLCao Liu
Cao Liu
BDBoqi Dai
Boqi Dai
Hai-Tao ZhengHai-Tao Zheng
Hai-Tao Zheng
HKHong-Gee Kim
Hong-Gee Kim
Multi-label unknown intent detection is a challenging task where each utterance may contain not only multiple known but also unknown intents. To tackle this challenge, pioneers proposed to predict the intent number of the utterance first, then compare it with the results of known intent matching to decide whether the utterence contains unknown intent(s). Though they have made remarkable progress on this task, their methods still suffer from two important issues: (1) It is inadequate to extract multiple intents using only utterance encoding; (2) Optimizing two sub-tasks (intent number prediction and known intent matching) independently leads to inconsistent predictions. In this article, we propose to incorporate segment augmentation rather than only use utterance encoding to better detect multiple intents. We also design a prediction consistency module to bridge the gap between the two sub-tasks. Empirical results on MultiWOZ2.3 and MixSNIPS datasets show that our method achieves state-of-the-art performance and significantly improves the best baseline.

31 July 2023 in Journal of Computer Science and Technology
Verified
Journal Article
Closed access
PDF file
QLQing-Bin Liu
Qing-Bin Liu
SHShizhu He
Shizhu He
CLCao Liu
Cao Liu
KLKang Liu
Kang Liu
JZJun Zhao
Jun Zhao