arXiv 2312.037562023-12-04cs.CLcs.AIcs.HCcs.LG

LineConGraphs：利用图神经网络实现有效情感识别的线性对话图

LineConGraphs: Line Conversation Graphs for Effective Emotion Recognition using Graph Neural Networks

IIT Madras（印度理工学院马德拉斯分校）；National Institute of Standards and Technology（美国国家标准与技术研究院）；University of Maryland, College Park（马里兰大学帕克分校）

Gokul S Krishnan, Sarala Padi, Craig S. Greenberg, Balaraman Ravindran, Dinesh Manoch, Ram D. Sriram

备注：: 13 pages, 6 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对ERC中说话者依赖和长上下文干扰问题，本文提出仅含相邻话语的说话者无关LineConGraphs及LineConGCN、LineConGAT模型，在IEMOCAP和MELD上取得SOTA性能。

摘要：

对话中的情感识别（Emotion Recognition in Conversations，ERC）是情感计算的一个关键方面，在医疗保健、教育、聊天机器人和社交媒体平台中具有许多实际应用。早期的ERC分析方法涉及使用图神经网络架构对说话者和长期上下文信息进行建模。然而，对于实际应用而言，部署与说话者无关的模型是理想选择。此外，较长的上下文窗口可能会在识别对话中某一话语的情感时造成混淆。为克服这些局限，我们提出了用于ERC分析的新型线性对话图卷积网络（LineConGCN）和图注意力网络（LineConGAT）模型。这些模型与说话者无关，并基于一种对话图构建策略——线性对话图（LineConGraphs）构建。LineConGraphs中的对话上下文是短期的，仅限于前一个和后一个话语，且说话者信息不属于该图的一部分。我们在两个基准数据集IEMOCAP和MELD上评估了所提模型的性能，并表明我们的LineConGAT模型以64.58%和76.50%的F1分数优于最先进方法。此外，我们证明，将情感转移信息嵌入线性对话图中，可进一步提升GCN模型在ERC任务上的性能。

英文摘要：

Emotion Recognition in Conversations (ERC) is a critical aspect of affective computing, and it has many practical applications in healthcare, education, chatbots, and social media platforms. Earlier approaches for ERC analysis involved modeling both speaker and long-term contextual information using graph neural network architectures. However, it is ideal to deploy speaker-independent models for real-world applications. Additionally, long context windows can potentially create confusion in recognizing the emotion of an utterance in a conversation. To overcome these limitations, we propose novel line conversation graph convolutional network (LineConGCN) and graph attention (LineConGAT) models for ERC analysis. These models are speaker-independent and built using a graph construction strategy for conversations -- line conversation graphs (LineConGraphs). The conversational context in LineConGraphs is short-term -- limited to one previous and future utterance, and speaker information is not part of the graph. We evaluate the performance of our proposed models on two benchmark datasets, IEMOCAP and MELD, and show that our LineConGAT model outperforms the state-of-the-art methods with an F1-score of 64.58% and 76.50%. Moreover, we demonstrate that embedding sentiment shift information into line conversation graphs further enhances the ERC performance in the case of GCN models.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。