SKIER: A Symbolic Knowledge Integrated Model for Conversational Emotion Recognition

Abstract

Emotion recognition in conversation (ERC) has received increasing attention from the research community. However, the ERC task is challenging, largely due to the complex and unstructured properties of multi-party conversations. Besides, the majority of daily dialogues take place in a specific context or circumstance, which requires rich external knowledge to understand the background of a certain dialogue. In this paper, we address these challenges by explicitly modeling the discourse relations between utterances and incorporating symbolic knowledge into multi-party conversations. We first introduce a dialogue parsing algorithm into ERC and further improve the algorithm through a transfer learning method. Moreover, we leverage different symbolic knowledge graph relations to learn knowledge-enhanced features for the ERC task. Extensive experiments on three benchmarks demonstrate that both dialogue structure graphs and symbolic knowledge are beneficial to the model performance on the task. Additionally, experimental results indicate that the proposed model surpasses baseline models on several indices.

Harnessing Holistic Discourse Features and Triadic Interaction for Sentiment Quadruple Extraction in Dialogues

“…The significance of speaker roles, providing insights into emotional states, is discussed in (Majumder et al 2019;He et al 2021). Efforts integrating external knowledge are seen in (Ren et al 2020;Zhan et al 2021;Li et al 2023b), while syntactic parsing techniques are explored by (Fei et al 2022b;Chen and Miyao 2022). Graph-based models, useful for tasks like emotion recognition and dialogue generation, are presented in (Shen et al 2021;Hu et al 2021;Chen et al 2020;Feng et al 2022;Lin et al 2021;Liang et al 2021).…”