ERNetCL: A novel emotion recognition network in textual conversation based on curriculum learning strategy

التفاصيل البيبلوغرافية
العنوان:	ERNetCL: A novel emotion recognition network in textual conversation based on curriculum learning strategy
المؤلفون:	Li, Jiang, Wang, Xiaoping, Liu, Yingjian, Zeng, Zhigang
سنة النشر:	2023
المجموعة:	Computer Science
مصطلحات موضوعية:	Computer Science - Computation and Language
الوصف:	Emotion recognition in conversation (ERC) has emerged as a research hotspot in domains such as conversational robots and question-answer systems. How to efficiently and adequately retrieve contextual emotional cues has been one of the key challenges in the ERC task. Existing efforts do not fully model the context and employ complex network structures, resulting in limited performance gains. In this paper, we propose a novel emotion recognition network based on curriculum learning strategy (ERNetCL). The proposed ERNetCL primarily consists of temporal encoder (TE), spatial encoder (SE), and curriculum learning (CL) loss. We utilize TE and SE to combine the strengths of previous methods in a simplistic manner to efficiently capture temporal and spatial contextual information in the conversation. To ease the harmful influence resulting from emotion shift and simulate the way humans learn curriculum from easy to hard, we apply the idea of CL to the ERC task to progressively optimize the network parameters. At the beginning of training, we assign lower learning weights to difficult samples. As the epoch increases, the learning weights for these samples are gradually raised. Extensive experiments on four datasets exhibit that our proposed method is effective and dramatically beats other baseline models. Comment: Accepted by Knowledge-Based Systems (KBS)
نوع الوثيقة:	Working Paper
DOI:	10.1016/j.knosys.2024.111434
URL الوصول:	http://arxiv.org/abs/2308.06450
رقم الأكسشن:	edsarx.2308.06450
قاعدة البيانات:	arXiv

الوصف
DOI:	10.1016/j.knosys.2024.111434