no code implementations • Findings (EMNLP) 2021 • Yuzhao Mao, Guang Liu, Xiaojie Wang, Weiguo Gao, Xuan Li
Emotion dynamics formulates principles explaining the emotional fluctuation during conversations.
no code implementations • 29 Sep 2021 • Wenming Cao, Qifan Liu, Guang Liu, Zhihai He
We construct a prime-dual network structure for few-shot learning which establishes a commutative relationship between the support set and the query set, as well as a new self- supervision constraint for highly effective few-shot learning.
no code implementations • 24 Sep 2021 • Guang Liu, Hailong Huang, Yuzhao Mao, Weiguo Gao, Xuan Li, Jianping Shen
Previous studies mostly use a fine-tuned Language Model (LM) to strengthen the constraints but ignore the fact that the potential of diversity could improve the effectiveness of generated data.
1 code implementation • EMNLP 2021 • Guang Liu, Yuzhao Mao, Hailong Huang, Weiguo Gao, Xuan Li
To address these issues, we propose the Adversarial Mixing Policy (AMP), organized in a min-max-rand formulation, to relax the Locally Linear Constraints in Mixup.
no code implementations • 15 Oct 2020 • Yuzhao Mao, Qi Sun, Guang Liu, Xiaojie Wang, Weiguo Gao, Xuan Li, Jianping Shen
Emotion Recognition in Conversations (ERC) is essential for building empathetic human-machine systems.
Ranked #7 on
Emotion Recognition in Conversation
on IEMOCAP
no code implementations • 8 Jul 2020 • Zheng Li, Gang Tu, Guang Liu, Zhi-Qiang Zhan, Yi-Jian Liu
The algorithm can not only introduce background knowledge, recognize all kinds of nested phrases in sentences, but also recognize the dependency between phrases.
no code implementations • 7 Jul 2020 • Guang Liu, Gang Tu, Zheng Li, Yi-Jian Liu
At present, most Natural Language Processing technology is based on the results of Word Segmentation for Dependency Parsing, which mainly uses an end-to-end method based on supervised learning.
no code implementations • 3 Mar 2020 • Jingyuan Yang, Guang Liu, Yuzhao Mao, Zhiwei Zhao, Weiguo Gao, Xuan Li, Haiqin Yang, Jianping Shen
Task 1 of the DSTC8-track1 challenge aims to develop an end-to-end multi-domain dialogue system to accomplish complex users' goals under tourist information desk settings.