Hybrid Quantum-Classical NLP Framework for Emotion Recognition Tasks

Read full text Summarise with VIRAT
Authors: Dharaniraj VM, Jayasuriya R, Sivasankaramoorthy R, Stephen T, Abirami Murugappan
Cited by: 0
References: 6

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This project aims at developing a comprehensive hybrid quantum-classical NLP pipeline to solve the task of emotion recognition. For emotion recognition, this work makes use of a hybrid Quantum Recurrent Neural Network (QRNN) by combining classical embedding layers with parameterized quantum circuits based on well defined ansatzes. The primary goal of the project is to train VQCs for capturing the emotion associated with sentences. This work aims at combining the strong embedding generation ability of classical architectures with the expressive power of Quantum circuits that can capture complex dependencies across sequences. The designed Hybrid QRNN model integrates two important aspects namely the strength of RNNs for sequential modelling and the representational power of quantum circuits resulting in competitive performance for emotion recognition task while also utilising the quantum benefits. The results reveal the potential of QNLP for advancing the intersection of Quantum Computing and Natural Language Processing for quantum-accelerated downstream NLP applications.

Fields of Study & Subjects

Quantum Computing Algorithms and Architecture Sentiment Analysis and Opinion Mining Topic Modeling

Publication details

Journal / source
EPJ Web of Conferences
Volume
360
Pages
01008–01008
Publication date
23 March 2026
Language
EN