AutoML-Emo: Automatic Knowledge Selection Using Congruent Effect for Emotion Identification in Conversations
- 26 December 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 14 (3) , 1845-1856
Abstract
Emotion recognition in conversations (ERC) has wide applications in medical care, human-computer interaction, and other fields. Unlike the general task of emotion analysis, humans usually rely on context and commonsense knowledge to convey emotions in conversations. Only when the model can connect and fully utilize a large-scale commonsense knowledge base, it can better understand latent contents in conversations. Unfortunately, there is no available knowledge selection mechanism to address such knowledge needs and to make sure the system is not flooded with irrelevant commonsense knowledge. Therefore, we propose an AutoML strategy based on emotion congruent effect to select suitable knowledge and models, called AutoML-Emo. Global exploration and local exploitation-based selection mechanisms (G&LESM) are used for automatic knowledge selection. The transformer-based architecture search (TAS) is applied to model selection, the selected transformer-based model is employed to incorporate knowledge and capture context information in conversations. The experimental results show that AutoML-Emo can effectively enhance external knowledge in different sizes and domain datasets. Moreover, the selected transformer-based model derived from TAS is superior to the most advanced models.Keywords
Funding Information
- National Natural Science Foundation of China (62106136, 61902231)
- Natural Science Foundation of Guangdong Province (2019A1515010943)
- Basic and Applied Basic Research of Colleges and Universities in Guangdong Province (2019KZDZX1030)
- Li Ka Shing Foundation Cross-Disciplinary Research (2020LKSFG04D)
- Science and Technology Major Project of Guangdong Province (STKJ2021005, STKJ202209002)
- Opening Project of Guangdong Province Key Laboratory of Information Security Technology (2020B1212060078)
This publication has 51 references indexed in Scilit:
- Multi-level Multiple Attentions for Contextual Multimodal Sentiment Analysis2017
- Context-Dependent Sentiment Analysis in User-Generated Videos2017
- Lifelong Learning for Sentiment Classification2015
- The Stanford CoreNLP Natural Language Processing Toolkit2014
- Glove: Global Vectors for Word Representation2014
- Convolutional Neural Networks for Sentence Classification2014
- The Measurement of Affect, Mood, and Emotion2013
- Clustering-Based Adaptive Crossover and Mutation Probabilities for Genetic AlgorithmsIEEE Transactions on Evolutionary Computation, 2007
- Toward detecting emotions in spoken dialogsIEEE Transactions on Speech and Audio Processing, 2005
- Evidence for a three-factor theory of emotionsJournal of Research in Personality, 1977