Metraipolis › archive › dc_092d4ef77df9

NIR: Approximate Neural Instance Retrieval for ALCIQ — arXiv:2611.02842

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02842
License (as archived)
CC0-1.0
Archived
2026-11-03T11:22:57.544Z
SHA-256 of the archived text
caeda0627e9b0b67589ee1a141021e8b7a594acffdcbd7d83b3ab2f46fa1de58
Stable URL of this page
https://metraipolis.com/documento/dc_092d4ef77df9

How to cite

NIR: Approximate Neural Instance Retrieval for ALCIQ — arXiv:2611.02842 — arXiv (en), https://arxiv.org/abs/2611.02842 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_092d4ef77df9 (Metraipolis archive dc_092d4ef77df9, sha256 caeda0627e9b0b67589ee1a141021e8b7a594acffdcbd7d83b3ab2f46fa1de58)
BibTeX
@misc{dc092d4ef77df9,
  title = {NIR: Approximate Neural Instance Retrieval for ALCIQ — arXiv:2611.02842},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02842},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_092d4ef77df9; sha256 caeda0627e9b0b67589ee1a141021e8b7a594acffdcbd7d83b3ab2f46fa1de58},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02842. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Instance retrieval is the main bottleneck of concept-learning systems based on refinement operators. We present NIR, a family of neural instance retrievers for ALCIQ that output graded membership scores from knowledge graph embeddings. We compare tokenization-based encoders (GRU, LSTM, Transformer) with a Compositional encoder that mirrors DL operators via primitive sub-networks. On eight benchmarks, all variants approximate Pellet closely on complete knowledge bases, while the Transformer model is most robust under incompleteness. The source code of our approach is at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.02842 — 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 2026-11-03T11:02:37.648Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).