Alert button
Picture for Shanglin Lei

Shanglin Lei

Alert button

Towards Robust and Generalizable Training: An Empirical Study of Noisy Slot Filling for Input Perturbations

Oct 05, 2023
Jiachi Liu, Liwen Wang, Guanting Dong, Xiaoshuai Song, Zechen Wang, Zhengyang Wang, Shanglin Lei, Jinzheng Zhao, Keqing He, Bo Xiao, Weiran Xu

Figure 1 for Towards Robust and Generalizable Training: An Empirical Study of Noisy Slot Filling for Input Perturbations
Figure 2 for Towards Robust and Generalizable Training: An Empirical Study of Noisy Slot Filling for Input Perturbations
Figure 3 for Towards Robust and Generalizable Training: An Empirical Study of Noisy Slot Filling for Input Perturbations
Figure 4 for Towards Robust and Generalizable Training: An Empirical Study of Noisy Slot Filling for Input Perturbations
Viaarxiv icon

InstructERC: Reforming Emotion Recognition in Conversation with a Retrieval Multi-task LLMs Framework

Sep 22, 2023
Shanglin Lei, Guanting Dong, Xiaoping Wang, Keheng Wang, Sirui Wang

Figure 1 for InstructERC: Reforming Emotion Recognition in Conversation with a Retrieval Multi-task LLMs Framework
Figure 2 for InstructERC: Reforming Emotion Recognition in Conversation with a Retrieval Multi-task LLMs Framework
Figure 3 for InstructERC: Reforming Emotion Recognition in Conversation with a Retrieval Multi-task LLMs Framework
Figure 4 for InstructERC: Reforming Emotion Recognition in Conversation with a Retrieval Multi-task LLMs Framework
Viaarxiv icon

Watch the Speakers: A Hybrid Continuous Attribution Network for Emotion Recognition in Conversation With Emotion Disentanglement

Sep 19, 2023
Shanglin Lei, Xiaoping Wang, Guanting Dong, Jiang Li, Yingjian Liu

Figure 1 for Watch the Speakers: A Hybrid Continuous Attribution Network for Emotion Recognition in Conversation With Emotion Disentanglement
Figure 2 for Watch the Speakers: A Hybrid Continuous Attribution Network for Emotion Recognition in Conversation With Emotion Disentanglement
Figure 3 for Watch the Speakers: A Hybrid Continuous Attribution Network for Emotion Recognition in Conversation With Emotion Disentanglement
Figure 4 for Watch the Speakers: A Hybrid Continuous Attribution Network for Emotion Recognition in Conversation With Emotion Disentanglement
Viaarxiv icon