Enabling Quantum Natural Language Processing for Hindi Language

Naman Srivastava; Gaurang Belekar; Gautami Sanjay Naik; Sunil Saumya; Aswath Babu H

cs.CLDec 2, 2023

Enabling Quantum Natural Language Processing for Hindi Language

Authors: Naman Srivastava, Gaurang Belekar, Gautami Sanjay Naik, Sunil Saumya, Aswath Babu H

Organizations: IIIT Dharwad Dharwad, India

Abstract

Quantum Natural Language Processing (QNLP) is taking huge leaps in solving the shortcomings of classical Natural Language Processing (NLP) techniques and moving towards a more "Explainable" NLP system. The current literature around QNLP focuses primarily on implementing QNLP techniques in sentences in the English language. In this paper, we propose to enable the QNLP approach to HINDI, which is the third most spoken language in South Asia. We present the process of building the parameterized quantum circuits required to undertake QNLP on Hindi sentences. We use the pregroup representation of Hindi and the DisCoCat framework to draw sentence diagrams. Later, we translate these diagrams to Parameterised Quantum Circuits based on Instantaneous Quantum Polynomial (IQP) style ansatz. Using these parameterized quantum circuits allows one to train grammar and topic-aware sentence classifiers for the Hindi Language.

Figures & tables

Symbol	Meaning
$\pi$	Personal Pronoun
n	Noun Phrase
p	Simple Predicate
a	Adjective
o	Object or Transitive Verb
$k_{1}$	Karaka

TABLE I: Pregroup Notations

Fig. 1: Standard Quantum Natural Language Pipeline

Fig. 2: String Diagram for Hindi Sentences

Fig. 3: Diagram for Sentence 1, single wired states are of type b and multiple wired are of type d.

Fig. 4: Diagram for Sentence 2, single wired states are of type b and multiple wired are of type d.

Fig. 5: Ansatz for word with single wire

Fig. 6: Ansatz for word with multiple wire

Fig. 7: PQC for ”Main School Jata hu”, end gates are measurements leading to information to classical register ”c” shown at the bottom.

Fig. 8: PQC for ”Mukesh ne khana khaya”, end gates are measurements leading to information to classical register ”c” shown at the bottom.

Fig. 9: Hybrid Quantum Neural Network for Quantum Natural Language Processing

Fig. 10: Epoch v/s Loss for training the model on a toy dataset

Explore similar work

What Does It Cost to Simulate a Quantum Sentence Classifier? An Energy and Compute Perspective on Near-Term QNLP
Oct 5, 2026Kishlay Kashyap, Sandipan GangulyQuantum Machine Learning Quantum Circuit Simulation
Heritage Institute of Technology
Variational Quantum Transformer Architecture for Synthetic Language Generation
Sep 16, 2026Julian Hager, Michael Kölle, Gerhard Stenzel +3Quantum Machine Learning Autoregressive Language Modeling
Institute of Informatics, LMU Munich, Oettingenstraße 67, 80538 Munich, Germany
Hybrid Quantum-Classical NLP Classification with Compact Semantic Representations: An Experimental Analysis of Representation Compression
Sep 9, 2026Ali Hassan, Zijia Zhao, Maha A. MetaweiHybrid Quantum-Classical ML Text Classification
German University in Cairo, Cairo, Egypt · University of Melbourne, Melbourne, Australia · High Performance Computing Lab, Electronics Research Institute, Cairo, Egypt

Oct 5, 2026, quant-phJ/K move · Enter open · S save

What Does It Cost to Simulate a Quantum Sentence Classifier? An Energy and Compute Perspective on Near-Term QNLP

Kishlay Kashyap, Sandipan Ganguly

Heritage Institute of Technology

Quantum Machine Learning Quantum Circuit Simulation Variational Quantum Circuits

Open paper AskPDF arXiv

Near-term quantum natural language processing (QNLP) experiments often run on classical simulators, so simulator cost is part of the field's practical compute burden, yet accuracy tables do not show it. We measure that cost for a variational quantum classifier (VQC) on binary SST-2 sentiment classification, using PennyLane's state-vector simulator over a controlled grid of 27 configurations: three balanced training-set sizes (N = 200, 500, 1000), three qubit counts (4, 6, 8), and three circuit depths. Each VQC is compared with logistic regression on the same PCA-reduced input; full TF-IDF logistic regression gives an uncompressed reference. The VQC beats its matched baseline in 6 of 27 single-seed comparisons. After reruns at two further seeds, only 1 of these 6 keeps a positive mean advantage larger than its paired seed-to-seed variability, and paired tests on the fixed validation set do not establish it. VQC training is 886-21,127 times slower in measured wall-clock time than the matched classical fit (median 3,158 times); going from 4 to 8 qubits roughly doubles simulator time, and within the tested range per-step cost is well approximated by a linear function of the parameter count. CodeCarbon energy and CO2 estimates are secondary: they imply an almost constant power of about 41 W, so they add little beyond runtime, and we do not build an energy ratio from them. The study is narrow (one dataset, representation, ansatz, simulator, and CPU environment) and is a reproducible feasibility measurement, not a general verdict on QNLP.

Abstract

Explore similar work

What Does It Cost to Simulate a Quantum Sentence Classifier? An Energy and Compute Perspective on Near-Term QNLP

Variational Quantum Transformer Architecture for Synthetic Language Generation

Hybrid Quantum-Classical NLP Classification with Compact Semantic Representations: An Experimental Analysis of Representation Compression