Quantum-inspired Neural Network for Conversational Emotion Recognition

Authors

  • Qiuchi Li University of Padua
  • Dimitris Gkoumas The Open University
  • Alessandro Sordoni Microsoft Research
  • Jian-Yun Nie Université de Montréal
  • Massimo Melucci University of Padua

Keywords:

Language Grounding & Multi-modal NLP

Abstract

We provide a novel perspective on conversational emotion recognition by drawing an analogy between the task and a complete span of quantum measurement. We characterize different steps of quantum measurement in the process of recognizing speakers' emotions in conversation, and stitch them up with a quantum-like neural network. The quantum-like layers are implemented by complex-valued operations to ensure an authentic adoption of quantum concepts, which naturally enables conversational context modeling and multimodal fusion. We borrow an existing algorithm to learn the complex-valued network weights, so that the quantum-like procedure is conducted in a data-driven manner. Our model is comparable to state-of-the-art approaches on two benchmarking datasets, and provide a quantum view to understand conversational emotion recognition.

Downloads

Published

2021-05-18

How to Cite

Li, Q., Gkoumas, D., Sordoni, A., Nie, J.-Y., & Melucci, M. (2021). Quantum-inspired Neural Network for Conversational Emotion Recognition. Proceedings of the AAAI Conference on Artificial Intelligence, 35(15), 13270-13278. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17567

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing II