COSMIC: COmmonSense knowledge for eMotion Identification in Conversations

By Deepanway Ghosal, Navonil Majumder, Alexander Gelbukh, Rada Mihalcea, Soujanya Poria. Findings, 2020

418 citations recorded by the source corpus.

In this paper, we address the task of utterance level emotion recognition in conversations using commonsense knowledge. We propose COSMIC, a new framework that incorporates different elements of commonsense such as mental states, events, and causal relations, and build upon them to learn interactions between interlocutors participating in a conversation. Current state-of-theart methods often encounter difficulties in context propagation, emotion shift detection, and differentiating between related emotion classes. By learning distinct commonsense representations, COSMIC addresses these challenges and achieves new state-of-the-art results for emotion recognition on four different benchmark conversational datasets. Our code is available at https://github.com/declare-lab/conv-emotion.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/4236663e6416423fca02d5b058302adcb78f51f3

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

1. Pearl Huan Z. Pu
2. Siyue Wu
3. Yunyi Yang
4. Yan Xiao
5. Yubo Xie
6. Fahui Miao
7. Zonghui Liu
8. Zongyang Ma

Citations in the corpus

• Natural Language Processing with Commonsense Knowledge: A Survey (2021, methodology): “Ghosal et al. [9] introduced the COSMIC framework, designed to enhance utterance-level emotion recognition in conversations by incorporating commonsense knowledge.”
• Directed Acyclic Graph Network for Conversational Emotion Recognition (2021, methodology): “, 2020), and COSMIC without external knowledge3 (Ghosal et al., 2020).”