Hybrid Curriculum Learning for Emotion Recognition in Conversation
改论文发表于2022 AAAI，阿里巴巴团队，旨在用课程学习解决对话情感识别
动机：
Motivated by recent studies which have proven that feeding training examples in a meaningful order rather than considering them randomly can boost the performance of models, we propose an ERCoriented hybrid curriculum learning framework.
贡献：
- We propose a hybrid curriculum learning framework to tackle the task of ERC. At conversation-level curriculum, we utilize an emotion-shift frequency to measure the difficulty of each conversation.
- We propose emotion-similarity based curriculum learning to achieve utterance-level curriculum learning. It implements the basic idea that at early stage of training it is less important to distinguish between similar emotions compared to separating very different emotions
- 理解这一点：在训练的早期，识别不同的情绪比区分相似的情绪更重要。那么为什么文章的方法能达到这个效果呢？
- 实验结果的有效性，实现了SOTA
方法：
(1) conversation-level curriculum (CC) – we construct a difficulty measurer based on “emotion shift”frequency. The conversations are scheduled in an “easy to hard” schema according to the difficulty score returned by the difficulty measurer.
(2) utterance-level curriculum (UC). it is implemented from an emotion-similarity perspective, which progressively strengthens the model’s ability in identifying the confusing emotions
UC很容易理解，就是常规的课程学习方法；UU的动机是说一个对话中的句子是具有逻辑性的，顺序是无法改变的，怎么解决这个问题呢？
作者assuming that the utterances with confusing emotion labels are more difficult for prediction;
and our utterance-level curriculum is based on the pairwise similarities between the emotion labels.
见下文：
首先计算一个情感矩阵：
进行归一化之后，得到目标情感矩阵概率分布，然后计算loss：
我理解的这个loss和之前的model相比应该就是增加了一个，可是和动机的关系是？没太理解。
整个过程的训练算法如下：
问题总结：
第一，对于动机2着实没理解透彻，为啥引入一个，可以起到课程学习的作用？解决方法和motivation之间的关联性是什么？
第二，对于算法中的第9~11行之间的矩阵的更新，我的理解是让这个矩阵对角线上逐步趋近于1，然而这个更新的方式也是没太明白。
懂的同学可以解释一下，谢谢！
更多有趣的文章见：
使用逆向思维的机器阅读理解
证据推理网络
Bert预训练模型-中文文本分类
文章出处登录后可见！
