Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2307.11788 · IEEE International Conference on Quantum Computing and Engineering (QCE)

Applying QNLP to Sentiment Analysis in Finance

Jonas Stein, I. Christ, Nicolas Kraus, Maximilian Balthasar Mansky, Robert Müller, Claudia Linnhoff–Popien

Published Sep 17, 2023• 42 citations
arXivHTMLPDF

Abstract

As an application domain where the slightest qualitative improvements can yield immense value, finance is a promising candidate for early quantum advantage. Focusing on the rapidly advancing field of Quantum Natural Language Processing (QNLP), we explore the practical applicability of the two central approaches DisCoCat (Distributional Compositional Categorical) and Quantum-Enhanced Long Short-Term Memory (QLSTM) to the problem of sentiment analysis in finance. Utilizing a novel ChatGPT-based data generation approach, we conduct a case study with more than 1000 realistic sentences and find that QLSTMs can be trained substantially faster than DisCoCat while also achieving close to classical results for their available software implementations.

DOI
10.1109/qce57702.2023.10178

Related papers

An Exploratory Evaluation of LLM-Assisted Rewriting of Moderate-Complexity Financial Sentences for DisCoCat-Based Sentiment Analysis

Brian Llinas, Nikos Chrisochoides

Quantum natural language processing (QNLP) provides a grammar-aware framework for text modeling, and Distributional Compositional Categorical (DisCoCat) is one of its theoretically grounded formulations. Prior work on financial sentiment analysis has identified practical limitations of DisCoCat, including parser sensitivity, high simulation cost, and difficulty handling longer sentences. We study an LLM-assisted preprocessing workflow that uses controlled rewriting to compress, simplify, or decompose moderate-complexity financial sentiment sentences into parser-compatible, circuit-efficient variants while preserving sentiment-bearing meaning. We compare prompting strategies, language models, and filtering configurations with the low-complexity-only DisCoCat baseline of Stein et al. At the circuit level, the strongest compression variants reduce average qubit and gate counts by more than 70 percent relative to the raw moderate-complexity subset. Across repeated training runs, GPT-4.1-mini with Prompt B achieves the highest observed mean accuracy, $0.550 \pm 0.035$, compared with $0.521 \pm 0.050$ for the baseline. Larger training splits do not necessarily improve downstream performance; across evaluated configurations, training-split size has a moderately negative association with accuracy (Pearson $r=-0.446$). These results provide exploratory evidence that LLM-assisted rewriting can make some moderate-complexity inputs usable within the evaluated DisCoCat configuration, while highlighting prompt design, filtering, and circuit-aware preprocessing as considerations for more scalable QNLP-based financial sentiment analysis.

cs.CLCross-listedarXiv:2608.07439•Aug 10, 2026•0 citations

Experimentation on Various Sentiment Classification Models in Quantum Natural Language Processing

Muddada Muralikrishna, S Nandini, Hima Keerthi Sagiraju +2 more

Quantum computers has the capacity to enhance the speed of intricate calculations, achieve parallelism via superpositions, and effectively process vast amounts of data. In addition, the domain of natural language processing (NLP) is swiftly drawing the attention of academics and engineers that want to construct more extensive computational models for NLP. Hence, the use of quantum technology in NLP endeavours, particularly in sentiment categorization, has promising prospects for further advancement. In this research work, a detailed analysis of different sentiment classification methods are investigated that are interpreted with quantum computing models. To be precise the Quantum Long Short Term Memory (QLSTM) and Quantum Support Vector Machines (QSVM) are examined to determine the efficiency among the models. The results are simulated in Qiskit simulator and real time quantum computer Qiskit_ibm_osaka to evaluate the examined models. The results shows the significance of the experimentation and it is proven using Accuracy, precision and recall as performance metrices. On an average, in terms of accuracy the proposed model outperforms existing methods with 8.9%, On precision the proposed model outperforms 11.1% compared to existing methods. And with respect to recall the proposed model outperforms 6.7% compared to existing methods.

International Conference on Augmented Reality, Intelligent Systems, and Industrial Automation (ARIIA)•Dec 20, 2024•0 citations

Quantum Natural Language Processing Based Sentiment Analysis Using Lambeq Toolkit

Srinjoy Ganguly, Sai Nandan Morapakula, Luis Miguel Pozo Coronado

Sentiment classification is one of the best use cases of classical natural language processing (NLP). We witness its power in various domains such as banking, business, and the marketing industry. We already know how classical AI and machine learning can change and improve technology. Quantum natural language processing (QNLP) is a young and gradually emerging technology that can provide a quantum advantage for NLP tasks. In this paper, we show the first application of QNLP for sentiment analysis and achieve perfect test set accuracy for three different kinds of simulations and decent accuracy for experiments run on a noisy quantum device. We utilize the lambeq QNLP toolkit and t|ket > by Cambridge Quantum (Quantinuum) to produce the results.

arXiv:2305.19383•International Conference on Power, Control and Computing Technologies (ICPC2T)•Mar 1, 2022•29 citations

A Survey of Quantum Natural Language Processing: From Compositional Models to NISQ-Era Empiricism

Arpan Phukan, Asif Ekbal

Quantum Natural Language Processing (QNLP) has emerged as a novel paradigm that leverages the principles of quantum mechanics to address fundamental challenges in language modeling, particularly in capturing compositional meaning.This survey charts the evolution of QNLP, from its theoretical foundations in the Distributional Compositional Categorical (DisCoCat) framework to its modern implementation on Noisy Intermediate-Scale Quantum (NISQ) hardware.We review the primary architectural approaches, including variational quantum circuits and tensor networks, and summarize the growing body of empirical work in tasks such as text classification, sentence similarity, and question answering.A recurring finding is the potential for QNLP models to achieve competitive performance with significantly fewer parameters than their classical counterparts.However, the field is critically constrained by the limitations of NISQ-era hardware.We conclude by discussing these challenges and outlining the future trajectory towards achieving a demonstrable quantum advantage and building more interpretable, efficient language models.

•Jan 1, 2025•0 citations

Toward Quantum-Enhanced Natural Language Understanding: Sarcasm and Claim Detection with QLSTM

Pritam Pal, Dipankar Das

Traditional machine learning (ML) and deep learning (DL) models have shown effectiveness in natural language processing (NLP) tasks, such as sentiment analysis.However, they often struggle with complex linguistic structures, such as sarcasm and implicit claims.This paper introduces a Quantum Long Short-Term Memory (QLSTM) framework for detecting sarcasm and identifying claims in text, aiming to enhance the analysis of complex sentences.We evaluate four approaches: (1) classical LSTM, (2) quantum framework using QLSTM, (3) voting ensemble combining classical and quantum LSTMs, and (4) hybrid framework integrating both types.The experimental results indicate that the QLSTM approach excels in sarcasm detection, while the voting framework performs best in claim identification.

International conference Recent advances in natural language processing•Jan 1, 2025•2 citations

A gentle introduction to Quantum Natural Language Processing

Shervin Le Du, Senaida Hernández Santana, Scarpa, Giannicola

The main goal of this master's thesis is to introduce Quantum Natural Language Processing (QNLP) in a way understandable by both the NLP engineer and the quantum computing practitioner. QNLP is a recent application of quantum computing that aims at representing sentences' meaning as vectors encoded into quantum computers. To achieve this, the distributional meaning of words is extended by the compositional meaning of sentences (DisCoCat model) : the vectors representing words' meanings are composed through the syntactic structure of the sentence. This is done using an algorithm based on tensor products. We see that this algorithm is inefficient on classical computers but scales well using quantum circuits. After exposing the practical details of its implementation, we go through three use-cases.

arXiv:2202.11766•Feb 23, 2022•4 citations
As an application domain where the slightest qualitative improvements can yield immense value, finance is a promising candidate for early quantum advantage. Focusing on the rapidly advancing field of Quantum Natural Language Processing (QNLP), we explore the practical applicability of the two central approaches DisCoCat (Distributional Compositional Categorical) and Quantum-Enhanced Long Short-Term Memory (QLSTM) to the problem of sentiment analysis in finance. Utilizing a novel ChatGPT-based data generation approach, we conduct a case study with more than 1000 realistic sentences and find that QLSTMs can be trained substantially faster than DisCoCat while also achieving close to classical results for their available software implementations.
Quantum natural language processing (QNLP) provides a grammar-aware framework for text modeling, and Distributional Compositional Categorical (DisCoCat) is one of its theoretically grounded formulations. Prior work on financial sentiment analysis has identified practical limitations of DisCoCat, including parser sensitivity, high simulation cost, and difficulty handling longer sentences. We study an LLM-assisted preprocessing workflow that uses controlled rewriting to compress, simplify, or decompose moderate-complexity financial sentiment sentences into parser-compatible, circuit-efficient variants while preserving sentiment-bearing meaning. We compare prompting strategies, language models, and filtering configurations with the low-complexity-only DisCoCat baseline of Stein et al. At the circuit level, the strongest compression variants reduce average qubit and gate counts by more than 70 percent relative to the raw moderate-complexity subset. Across repeated training runs, GPT-4.1-mini with Prompt B achieves the highest observed mean accuracy, 0.550±0.0350.550 \pm 0.0350.550±0.035, compared with 0.521±0.0500.521 \pm 0.0500.521±0.050 for the baseline. Larger training splits do not necessarily improve downstream performance; across evaluated configurations, training-split size has a moderately negative association with accuracy (Pearson r=−0.446r=-0.446r=−0.446). These results provide exploratory evidence that LLM-assisted rewriting can make some moderate-complexity inputs usable within the evaluated DisCoCat configuration, while highlighting prompt design, filtering, and circuit-aware preprocessing as considerations for more scalable QNLP-based financial sentiment analysis.
Quantum computers has the capacity to enhance the speed of intricate calculations, achieve parallelism via superpositions, and effectively process vast amounts of data. In addition, the domain of natural language processing (NLP) is swiftly drawing the attention of academics and engineers that want to construct more extensive computational models for NLP. Hence, the use of quantum technology in NLP endeavours, particularly in sentiment categorization, has promising prospects for further advancement. In this research work, a detailed analysis of different sentiment classification methods are investigated that are interpreted with quantum computing models. To be precise the Quantum Long Short Term Memory (QLSTM) and Quantum Support Vector Machines (QSVM) are examined to determine the efficiency among the models. The results are simulated in Qiskit simulator and real time quantum computer Qiskit_ibm_osaka to evaluate the examined models. The results shows the significance of the experimentation and it is proven using Accuracy, precision and recall as performance metrices. On an average, in terms of accuracy the proposed model outperforms existing methods with 8.9%, On precision the proposed model outperforms 11.1% compared to existing methods. And with respect to recall the proposed model outperforms 6.7% compared to existing methods.
Sentiment classification is one of the best use cases of classical natural language processing (NLP). We witness its power in various domains such as banking, business, and the marketing industry. We already know how classical AI and machine learning can change and improve technology. Quantum natural language processing (QNLP) is a young and gradually emerging technology that can provide a quantum advantage for NLP tasks. In this paper, we show the first application of QNLP for sentiment analysis and achieve perfect test set accuracy for three different kinds of simulations and decent accuracy for experiments run on a noisy quantum device. We utilize the lambeq QNLP toolkit and t|ket > by Cambridge Quantum (Quantinuum) to produce the results.
Quantum Natural Language Processing (QNLP) has emerged as a novel paradigm that leverages the principles of quantum mechanics to address fundamental challenges in language modeling, particularly in capturing compositional meaning.This survey charts the evolution of QNLP, from its theoretical foundations in the Distributional Compositional Categorical (DisCoCat) framework to its modern implementation on Noisy Intermediate-Scale Quantum (NISQ) hardware.We review the primary architectural approaches, including variational quantum circuits and tensor networks, and summarize the growing body of empirical work in tasks such as text classification, sentence similarity, and question answering.A recurring finding is the potential for QNLP models to achieve competitive performance with significantly fewer parameters than their classical counterparts.However, the field is critically constrained by the limitations of NISQ-era hardware.We conclude by discussing these challenges and outlining the future trajectory towards achieving a demonstrable quantum advantage and building more interpretable, efficient language models.
Traditional machine learning (ML) and deep learning (DL) models have shown effectiveness in natural language processing (NLP) tasks, such as sentiment analysis.However, they often struggle with complex linguistic structures, such as sarcasm and implicit claims.This paper introduces a Quantum Long Short-Term Memory (QLSTM) framework for detecting sarcasm and identifying claims in text, aiming to enhance the analysis of complex sentences.We evaluate four approaches: (1) classical LSTM, (2) quantum framework using QLSTM, (3) voting ensemble combining classical and quantum LSTMs, and (4) hybrid framework integrating both types.The experimental results indicate that the QLSTM approach excels in sarcasm detection, while the voting framework performs best in claim identification.
The main goal of this master's thesis is to introduce Quantum Natural Language Processing (QNLP) in a way understandable by both the NLP engineer and the quantum computing practitioner. QNLP is a recent application of quantum computing that aims at representing sentences' meaning as vectors encoded into quantum computers. To achieve this, the distributional meaning of words is extended by the compositional meaning of sentences (DisCoCat model) : the vectors representing words' meanings are composed through the syntactic structure of the sentence. This is done using an algorithm based on tensor products. We see that this algorithm is inefficient on classical computers but scales well using quantum circuits. After exposing the practical details of its implementation, we go through three use-cases.