论文标题
监督原型的对比度学习，以识别对话
Supervised Prototypical Contrastive Learning for Emotion Recognition in Conversation
论文作者
论文摘要
在对话中捕捉情绪在现代对话系统中起着至关重要的作用。但是，情绪与语义之间的弱相关性为对话（ERC）中的情绪识别带来了许多挑战。即使是语义上相似的话语，情感也可能会根据上下文或演讲者而变化。在本文中，我们建议对ERC任务进行监督的原型对比度学习（SPCL）损失。利用原型网络，SPCL的目标是通过对比度学习解决不平衡的分类问题，并且不需要大批量大小。同时，我们根据类之间的距离设计了难度测量功能，并引入了课程学习以减轻极端样本的影响。我们在三个广泛使用的基准测试基准上实现了最先进的结果。此外，我们进行了分析实验，以证明我们提出的SPCL和课程学习策略的有效性。我们在https://github.com/caskcsg/spcl上发布代码。
Capturing emotions within a conversation plays an essential role in modern dialogue systems. However, the weak correlation between emotions and semantics brings many challenges to emotion recognition in conversation (ERC). Even semantically similar utterances, the emotion may vary drastically depending on contexts or speakers. In this paper, we propose a Supervised Prototypical Contrastive Learning (SPCL) loss for the ERC task. Leveraging the Prototypical Network, the SPCL targets at solving the imbalanced classification problem through contrastive learning and does not require a large batch size. Meanwhile, we design a difficulty measure function based on the distance between classes and introduce curriculum learning to alleviate the impact of extreme samples. We achieve state-of-the-art results on three widely used benchmarks. Further, we conduct analytical experiments to demonstrate the effectiveness of our proposed SPCL and curriculum learning strategy. We release the code at https://github.com/caskcsg/SPCL.
