Metraipolis › archive › dc_dbc4eb819412
Ontology-Driven Structural Regularization for Document-Level Relation Extraction — arXiv:2608.20856
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.20856
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T10:18:25.614Z
- SHA-256 of the archived text
2415c15f736356aedcb4af182c20d1936a907d4b2683236a60dc789b92551272- Stable URL of this page
https://metraipolis.com/documento/dc_dbc4eb819412
How to cite
Ontology-Driven Structural Regularization for Document-Level Relation Extraction — arXiv:2608.20856 — arXiv (en), https://arxiv.org/abs/2608.20856 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dbc4eb819412 (Metraipolis archive dc_dbc4eb819412, sha256 2415c15f736356aedcb4af182c20d1936a907d4b2683236a60dc789b92551272)
BibTeX
@misc{dcdbc4eb819412,
title = {Ontology-Driven Structural Regularization for Document-Level Relation Extraction — arXiv:2608.20856},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.20856},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dbc4eb819412; sha256 2415c15f736356aedcb4af182c20d1936a907d4b2683236a60dc789b92551272},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20856. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Document-Level Relation Extraction (DocRE) relies heavily on costly manually annotated datasets, while large distant supervision resources such as DocRED distant remain underexploited due to noise. We show that a critical yet overlooked source of noise lies in structural inconsistencies within relational triples, including violations of ontology constraints and logical contradictions. We introduce an ontology-driven framework to quantify and enforce structural consistency in DocRE datasets. Our analysis reveals substantial structural noise in DocRED distant and demonstrates that such inconsistencies propagate to model predictions. Enforcing structural well-formedness during training significantly reduces logical contradictions and consistently improves generalization performance. These findings establish structural consistency as a missing axis of supervision in DocRE and highlight structural regularization as an effective strategy for leveraging distant data at scale. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-24 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.20856 — 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 2026-10-18T10:17:37.586Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).