Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations

By Peixiang Zhong, Di Wang, Chunyan Miao. Conference on Empirical Methods in Natural Language Processing, 2019

307 citations recorded by the source corpus.

Messages in human conversations inherently convey emotions. The task of detecting emotions in textual conversations leads to a wide range of applications such as opinion mining in social networks. However, enabling machines to analyze emotions in conversations is challenging, partly because humans often rely on the context and commonsense knowledge to express emotions. In this paper, we address these challenges by proposing a Knowledge-Enriched Transformer (KET), where contextual utterances are interpreted using hierarchical self-attention and external commonsense knowledge is dynamically leveraged using a context-aware affective graph attention mechanism. Experiments on multiple textual conversation datasets demonstrate that both context and commonsense knowledge are consistently beneficial to the emotion detection performance. In addition, the experimental results show that our KET model outperforms the state-of-the-art models on most of the tested datasets in F1 score.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/ea0b7059e232aa3eb50da0a67ca3d41865f6926f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Directed Acyclic Graph Network for Conversational Emotion Recognition (2021, methodology): “Graph-based methods: DialogurGCN (Ghosal et al., 2019), KET (Zhong et al., 2019), DialogXL (Shen et al., 2020) and RGAT (Ishiwatari et al., 2020).”
KinGDOM: Knowledge-Guided DOMain Adaptation for Sentiment Analysis (2020, background): “Commonsense KBs, in particular, provide a rich source of background concepts–related by commonsense links–which can enhance the semantics of a piece of text by providing both domainspecific and domain-general concepts (Yang et al., 2019; Zhong et al., 2019; Agarwal et al., 2015; Zhong et al., 2019) ”
Natural Language Processing with Commonsense Knowledge: A Survey (2021, background): “Zhong et al. [7] represented a pioneering effort in integrating external commonsense knowledge for emotion detection within textual dialogues.”
DynaEval: Unifying Turn and Dialogue Level Evaluation (2021, background): “Sometimes, adding more context leads to diminishing performance gain or even negative impact (Zhong et al., 2019).”
A Knowledge-Aware Sequence-to-Tree Network for Math Word Problem Solving (2020, background): “Recently, many studies have used deep learning methods to incorporate external knowledge from the knowledge base into many NLP tasks, such as dialogue systems (Zhong et al., 2019) and reading comprehension (Wang and Jiang, 2019; Qiu et al., 2019).”
A Novel Cascade Binary Tagging Framework for Relational Triple Extraction (2019, background): “It is designed to learn deep representations by jointly conditioning on both left and right context of each word, and it has recently been proven surprisingly effective in many downstream tasks (Zhong et al., 2019).”
COSMIC: COmmonSense knowledge for eMotion Identification in Conversations (2020, methodology): “An external knowledge base was used in (Zhong et al., 2019) with transformer networks to perform emotion recognition.”
Knowledge Aware Emotion Recognition in Textual Conversations via Multi-Task Incremental Transformer (2020, methodology): “That KET doesn’t consider various relations in external knowledge base may cause the loss of semantic information.”