Výsledky vyhledávání - "Li, Shoushan"

Report

Comment-aided Video-Language Alignment via Contrastive Pre-training for Short-form Video Humor Detection

Autor: Liu, Yang, Shen, Tongfei, Zhang, Dong, Sun, Qingying, Li, Shoushan, Zhou, Guodong

The growing importance of multi-modal humor detection within affective computing correlates with the expanding influence of short-form video sharing on social media platforms. In this paper, we propose a novel two-branch hierarchical model for short-

Externí odkaz: http://arxiv.org/abs/2402.09055

Zobrazit plný text záznamu

Report

Pre-trained Token-replaced Detection Model as Few-shot Learner

Autor: Li, Zicheng, Li, Shoushan, Zhou, Guodong

Pre-trained masked language models have demonstrated remarkable ability as few-shot learners. In this paper, as an alternative, we propose a novel approach to few-shot learning with pre-trained token-replaced detection models like ELECTRA. In this ap

Externí odkaz: http://arxiv.org/abs/2203.03235

Zobrazit plný text záznamu

Akademický článek

Response generation in multi-modal dialogues with split pre-generation and cross-modal contrasting

Autor: Li, Linqin, Zhang, Dong, Zhu, Suyang, Li, Shoushan, Zhou, Guodong

Publikováno v: In Information Processing and Management January 2024 61(1)

Zobrazit plný text záznamu

Report

Human-Like Decision Making: Document-level Aspect Sentiment Classification via Hierarchical Reinforcement Learning

Autor: Wang, Jingjing, Sun, Changlong, Li, Shoushan, Wang, Jiancheng, Si, Luo, Zhang, Min, Liu, Xiaozhong, Zhou, Guodong

Recently, neural networks have shown promising results on Document-level Aspect Sentiment Classification (DASC). However, these approaches often offer little transparency w.r.t. their inner working mechanisms and lack interpretability. In this paper,

Externí odkaz: http://arxiv.org/abs/1910.09260

Zobrazit plný text záznamu

Report

Emotion Detection with Neural Personal Discrimination

Autor: Zhou, Xiabing, Wang, Zhongqing, Li, Shoushan, Zhou, Guodong, Zhang, Min

There have been a recent line of works to automatically predict the emotions of posts in social media. Existing approaches consider the posts individually and predict their emotions independently. Different from previous researches, we explore the de

Externí odkaz: http://arxiv.org/abs/1908.10703

Zobrazit plný text záznamu