Metraipolis › archive › dc_a15e4b1397ee
Reflective Compositional Grounding for Natural-Language-to-SPARQL — arXiv:2610.21796
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21796
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:40:14.429Z
- SHA-256 of the archived text
55d1a34baa5066eab2edaafce165a33f4ae85733043d1c913754232672311006- Stable URL of this page
https://metraipolis.com/documento/dc_a15e4b1397ee
How to cite
Reflective Compositional Grounding for Natural-Language-to-SPARQL — arXiv:2610.21796 — arXiv (en), https://arxiv.org/abs/2610.21796 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a15e4b1397ee (Metraipolis archive dc_a15e4b1397ee, sha256 55d1a34baa5066eab2edaafce165a33f4ae85733043d1c913754232672311006)
BibTeX
@misc{dca15e4b1397ee,
title = {Reflective Compositional Grounding for Natural-Language-to-SPARQL — arXiv:2610.21796},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21796},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a15e4b1397ee; sha256 55d1a34baa5066eab2edaafce165a33f4ae85733043d1c913754232672311006},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21796. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Natural-language query generation over large knowledge graphs embodies the classical vocabulary problem in human-systems communication. Questions express concepts through wording and compositions that can differ substantially from the target schema, while limited model context requires selective access to schema information. We present an NL2SPARQL framework that places conceptual compositionality at the center of query interpretation and connects it to the relational composition required for binding and query construction. A fixed concept encoder represents compound expressions jointly, and schema candidates are ranked using semantic similarity, type compatibility, and hierarchy proximity. Reflective refinement critically examines how the grounded meanings are realized through argument bindings, joins, and operator scope. Diagnosed semantic discrepancies guide revisions to the responsible stage. We formalise a monotone refinement discipline that accumulates scoped interpretation requirements and establish conditions under which changes to the composed process preserve previously validated interpretations. Across five benchmark/knowledge-graph targets, mean schema recall@10 increases from 0.712 to 0.837. With retrieval held fixed, reflective prompt rewriting adds 2.27-3.33 answer-F1 points. These experiments evaluate the grounding and refinement mechanisms, while the formal analysis specifies the stronger requirements for conservative adaptation across queries. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.DB, nuovi lavori del giorno). Categorie arXiv: Databases (cs.DB). Pagina del lavoro: https://arxiv.org/abs/2610.21796 — 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 2026-10-16T08:52:32.567Z dalla pagina https://arxiv.org/list/cs.DB/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).