Abstract

Emotion Recognition in Conversation (ERC) has gained much attention from the NLP community recently. Some models concentrate on leveraging commonsense knowledge or multi-task learning to help complicated emotional reasoning. However, these models neglect direct utterance-knowledge interaction. In addition, these models utilize emotion-indirect auxiliary tasks, which provide limited affective information for the ERC task. To address the above issues, we propose a Knowledge-Interactive Network with sentiment polarity intensity-aware multi-task learning, namely KI-Net, which leverages both commonsense knowledge and sentiment lexicon to augment semantic information. Specifically, we use a self-matching module for internal utterance-knowledge interaction. Considering correlations with the ERC task, a phrase-level Sentiment Polarity Intensity Prediction (SPIP) task is devised as an auxiliary task. Experiments show that all knowledge integration, self-matching and SPIP modules improve the model performance respectively on three datasets. Moreover, our KI-Net model shows 1.04% performance improvement over the state-of-the-art model on the IEMOCAP dataset.

Highlights

  • D sentiment lexicon to augment semantic information

  • We introduce a phrase-level Sentiment Polarity Intensity Prediction (SPIP) as the auxiliary task, which is expected to provide more direct instructions on emotion recognition of the target utterance

  • On emotions Neutral are essential for the Emotion Recognition in Conversation (ERC) task again

Read more

Summary

Related Work

Emotion recognition in conversation has gained attention from the NLP community only in the past few years (Yeh et al, 2019; Majumder et al, 2019; Zhou et al, 2018) since the growing availability of public conversational data (Busso et al, 2008; Poria et al, 2019a; Li et al, 2017). Transformer (Vaswani et al, 2017) has been devised to model input sequences in many recent works (Zhong et al, 2019; Zhang et al, 2020), which lead to better results. Modules such as memory networks (Wenxiang Jiao and King, 2020; Xing et al, 2020) and graph-based networks (Ghosal et al, 2019; Ishiwatari et al, 2020) are introduced for representation learning to better model contextual information and utterance dependencies. A self-matching module is employed for utterance-knowledge interac-

Task Definition and Model Overview
Context- and Dependency-Aware Encoder
Knowledge Introduction
Datasets
Baselines and State of the Art
Results and Analysis
Method
Error Analysis
Conclusion
Ablation Study

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.