Conversational Memory Network for Emotion Recognition in Dyadic Dialogue Videos.
Conversational Memory Network for Emotion Recognition in Dyadic Dialogue Videos.
复制标题
DOI：
10.18653/v1/n18-1193
复制
发表时间：
2018-06-01
期刊：
影响因子：
--
通讯作者：
Zimmermann, Roger
中科院分区：
文献类型：
--
作者：
Hazarika, Devamanyu;Poria, Soujanya;Zimmermann, Roger
会话中的情感识别对于开发具有同理心的机器至关重要。现有方法在对会话中的情感进行分类时，大多忽略了说话人之间的依存关系的作用。在这篇文章中，我们致力于识别二元对话视频中的话语级情感。我们提出了一种深层神经网络框架，称为会话记忆网络，它利用了会话历史中的上下文信息。该框架采用多模式方法，包括音频、视觉和文本特征，并使用门控循环单元将每个说话人的过去话语建模到记忆中。然后，使用基于注意力的跳跃来合并这些记忆，以捕获说话者之间的相关性。实验表明，精度比现有技术提高了3-4%。
Emotion recognition in conversations is crucial for the development of empathetic machines. Present methods mostly ignore the role of inter-speaker dependency relations while classifying emotions in conversations. In this paper, we address recognizing utterance-level emotions in dyadic conversational videos. We propose a deep neural framework, termed conversational memory network, which leverages contextual information from the conversation history. The framework takes a multimodal approach comprising audio, visual and textual features with gated recurrent units to model past utterances of each speaker into memories. Such memories are then merged using attention-based hops to capture inter-speaker dependencies. Experiments show an accuracy improvement of 3-4% over the state of the art.