{
  "abstract": "Quantum Natural Language Processing (QNLP) uses pregroup grammars to translate grammatical structure into diagrammatic representations and quantum circuits. Recent Hindi QNLP work has shown that Hindi-specific pregroup grammars can support grammar-sensitive compositional models, but grammatical type assignment is still largely manual, limiting scalability. This paper formulates automatic Hindi pregroup supertagging as a token-level classification task. Using a manually annotated corpus of 380 Hindi sentences, we evaluate lexical, contextual, prompting-based, lexical-repair, and suffix/morphology-aware methods. Results show that simple lexical and contextual models are strong in this low-resource setting: contextual backoff achieves the best completed accuracy of 64.56\\%, while raw Qwen2.5 prompting reaches only 11.65\\%. Lexical repair raises LLM-assisted prediction to 64.08\\%, demonstrating the value of constraining generative outputs with symbolic grammar knowledge. Diagnostic analysis further shows that seen and unambiguous tokens are much easier than unseen tokens, and suffix/morphology features improve karaka-token accuracy but not overall performance. These results show that automatic Hindi pregroup assignment is feasible and can reduce reliance on manual annotation in future multilingual QNLP pipelines.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.13721",
  "author_total": 4,
  "authors": [
    {
      "name": "Gautami Sanjay Naik"
    },
    {
      "name": "Krishna Bhatia"
    },
    {
      "name": "Mithun Paul Saint-Germain"
    },
    {
      "name": "H Aswath Babu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3mg9xp1ts8bp7.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.13721",
  "fulltext_url": null,
  "id": "3mg9xp1ts8bp7",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.13721",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CL"
    ],
    [
      "arxiv",
      "quant-ph"
    ],
    [
      "openalex",
      "1702|Natural Language Processing Techniques"
    ]
  ],
  "openalex": "W7213237062",
  "pdf_url": "https://arxiv.org/pdf/2609.13721",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-12",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/3mg9xp1ts8bp7.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:25Z",
      "native_id": "2609.13721",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.13721"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:quant-ph",
      "subfield": "quantum"
    }
  ],
  "title": "Scaling Hindi Quantum Natural Language Processing through Automatic Pregroup Supertagging",
  "title_text": "Scaling Hindi Quantum Natural Language Processing through Automatic Pregroup Supertagging",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:25Z",
  "url": "https://research.draconitic.com/paper/3mg9xp1ts8bp7",
  "venue": "arXiv",
  "versions": []
}