Quantum-Inspired Complex-Valued Language Models for Aspect-Based Sentiment Classification

Aiming at classifying the polarities over aspects, aspect-based sentiment analysis (ABSA) is a fine-grained task of sentiment analysis. The vector representations of current models are generally constrained to real values. Based on mathematical formulations of quantum theory, quantum language models...

Full description

Saved in:
Bibliographic Details
Published in:Entropy (Basel, Switzerland) Switzerland), 2022-04, Vol.24 (5), p.621
Main Authors: Zhao, Qin, Hou, Chenguang, Xu, Ruifeng
Format: Article
Language:English
Subjects:
aspect-based sentiment analysis
Classification
complexification
Data mining
Embedding
Food
Hilbert space
Language
Mathematical analysis
Neural networks
quantum language model
Quantum physics
Quantum theory
Representations
Semantics
Sentiment analysis
Signal processing
Vectors (mathematics)
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Aiming at classifying the polarities over aspects, aspect-based sentiment analysis (ABSA) is a fine-grained task of sentiment analysis. The vector representations of current models are generally constrained to real values. Based on mathematical formulations of quantum theory, quantum language models have drawn increasing attention. Words in such models can be projected as physical particles in quantum systems, and naturally represented by representation-rich complex-valued vectors in a Hilbert Space, rather than real-valued ones. In this paper, the Hilbert Space representation for ABSA models is investigated and the complexification of three strong real-valued baselines are constructed. Experimental results demonstrate the effectiveness of complexification and the outperformance of our complex-valued models, illustrating that the complex-valued embedding can carry additional information beyond the real embedding. Especially, a complex-valued RoBERTa model outperforms or approaches the previous state-of-the-art on three standard benchmarking datasets.
ISSN:1099-4300
1099-4300
DOI:10.3390/e24050621