Metraipolis › archive › dc_309bf1566768
Scaling Hindi Quantum Natural Language Processing through Automatic Pregroup Supertagging — arXiv:2609.13721
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.13721
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T23:14:44.934Z
- SHA-256 of the archived text
84122ec98ce52ee0ac10b9646277eec40a6c0fbaa45c3f0ddd7de24508a4f6c0- Stable URL of this page
https://metraipolis.com/documento/dc_309bf1566768
How to cite
Scaling Hindi Quantum Natural Language Processing through Automatic Pregroup Supertagging — arXiv:2609.13721 — arXiv (en), https://arxiv.org/abs/2609.13721 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_309bf1566768 (Metraipolis archive dc_309bf1566768, sha256 84122ec98ce52ee0ac10b9646277eec40a6c0fbaa45c3f0ddd7de24508a4f6c0)
BibTeX
@misc{dc309bf1566768,
title = {Scaling Hindi Quantum Natural Language Processing through Automatic Pregroup Supertagging — arXiv:2609.13721},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.13721},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_309bf1566768; sha256 84122ec98ce52ee0ac10b9646277eec40a6c0fbaa45c3f0ddd7de24508a4f6c0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13721. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Quantum Physics (quant-ph). Pagina del lavoro: https://arxiv.org/abs/2609.13721 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T22:51:09.832Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).