e5a532a8bc
- Introduced `test_nlp_extractor.py` with unit tests for the InstitutionExtractor, covering various extraction patterns (ISIL, Wikidata, VIAF, city names) and ensuring proper classification of institutions (museum, library, archive). - Added tests for extracted entities and result handling to validate the extraction process. - Created `test_partnership_rdf_integration.py` to validate the end-to-end process of extracting partnerships from a conversation and exporting them to RDF format. - Implemented tests for temporal properties in partnerships and ensured compliance with W3C Organization Ontology patterns. - Verified that extracted partnerships are correctly linked with PROV-O provenance metadata.
134 lines
4.8 KiB
YAML
134 lines
4.8 KiB
YAML
---
|
|
# Example: Open access preprint from arXiv on knowledge graph embeddings
|
|
# Reference: Rossi, A., et al. (2021). Knowledge Graph Embedding for Link Prediction:
|
|
# A Comparative Analysis. arXiv:2002.00819v3 [cs.AI]
|
|
|
|
- publication_id: https://arxiv.org/abs/2002.00819
|
|
title: "Knowledge Graph Embedding for Link Prediction: A Comparative Analysis"
|
|
publication_type: PREPRINT
|
|
|
|
authors:
|
|
- person_id: https://orcid.org/0000-0002-3061-2578
|
|
person_name: "Andrea Rossi"
|
|
orcid: "0000-0002-3061-2578"
|
|
affiliation:
|
|
organization_id: https://ror.org/01ggx4157
|
|
organization_name: "Politecnico di Milano"
|
|
ror_id: "https://ror.org/01ggx4157"
|
|
|
|
- person_id: https://orcid.org/0000-0001-9229-1653
|
|
person_name: "Donatella Firmani"
|
|
orcid: "0000-0001-9229-1653"
|
|
affiliation:
|
|
organization_id: https://ror.org/02be6w209
|
|
organization_name: "Sapienza University of Rome"
|
|
ror_id: "https://ror.org/02be6w209"
|
|
|
|
- person_id: https://orcid.org/0000-0002-4227-9654
|
|
person_name: "Antonio Matinata"
|
|
affiliation:
|
|
organization_id: https://ror.org/01ggx4157
|
|
organization_name: "Politecnico di Milano"
|
|
ror_id: "https://ror.org/01ggx4157"
|
|
|
|
- person_id: https://orcid.org/0000-0001-8103-8601
|
|
person_name: "Paolo Merialdo"
|
|
orcid: "0000-0001-8103-8601"
|
|
affiliation:
|
|
organization_id: https://ror.org/05ggb3n52
|
|
organization_name: "Università degli Studi Roma Tre"
|
|
ror_id: "https://ror.org/05ggb3n52"
|
|
|
|
- person_id: https://orcid.org/0000-0002-2295-5731
|
|
person_name: "Denilson Barbosa"
|
|
orcid: "0000-0002-2295-5731"
|
|
affiliation:
|
|
organization_id: https://ror.org/0160cpw27
|
|
organization_name: "University of Alberta"
|
|
ror_id: "https://ror.org/0160cpw27"
|
|
|
|
publication_date: "2021-02-03"
|
|
|
|
url: "https://arxiv.org/abs/2002.00819"
|
|
|
|
abstract: >-
|
|
Knowledge graph (KG) embedding techniques are now a widely adopted approach
|
|
to knowledge representation in which entities and relationships are embedded
|
|
into a continuous vector space. Existing models can be categorized as
|
|
translational distance models, semantic matching models, and models using
|
|
convolutional or recurrent neural networks. This paper provides a
|
|
comprehensive comparative analysis of 20 state-of-the-art KG embedding
|
|
models across 10 benchmark datasets.
|
|
|
|
keywords:
|
|
- "Knowledge Graph Embeddings"
|
|
- "Link Prediction"
|
|
- "Knowledge Representation"
|
|
- "Graph Neural Networks"
|
|
- "Benchmark Analysis"
|
|
- "TransE"
|
|
- "DistMult"
|
|
- "ComplEx"
|
|
|
|
open_access_status: FULLY_OPEN_ACCESS
|
|
license: "CC BY 4.0"
|
|
|
|
citations:
|
|
- citation_id: https://w3id.org/heritage/citation/kg-embed-cites-transe
|
|
citing_work: https://arxiv.org/abs/2002.00819
|
|
cited_work: https://proceedings.neurips.cc/paper/2013/hash/1cecc7a77928ca8133fa24680a88d2f9-Abstract.html
|
|
citation_type: CITES_AS_EVIDENCE
|
|
|
|
- citation_id: https://w3id.org/heritage/citation/kg-embed-cites-distmult
|
|
citing_work: https://arxiv.org/abs/2002.00819
|
|
cited_work: https://arxiv.org/abs/1412.6575
|
|
citation_type: REVIEWS
|
|
|
|
- citation_id: https://w3id.org/heritage/citation/kg-embed-extends
|
|
citing_work: https://arxiv.org/abs/2002.00819
|
|
cited_work: https://doi.org/10.1109/TKDE.2019.2950172
|
|
citation_type: EXTENDS
|
|
|
|
document_sections:
|
|
- section_id: https://w3id.org/heritage/section/kg-embed-abstract
|
|
section_type: ABSTRACT
|
|
section_title: "Abstract"
|
|
section_order: 0
|
|
|
|
- section_id: https://w3id.org/heritage/section/kg-embed-intro
|
|
section_type: INTRODUCTION
|
|
section_title: "Introduction"
|
|
section_order: 1
|
|
|
|
- section_id: https://w3id.org/heritage/section/kg-embed-background
|
|
section_type: INTRODUCTION
|
|
section_title: "Background and Related Work"
|
|
section_order: 2
|
|
|
|
- section_id: https://w3id.org/heritage/section/kg-embed-models
|
|
section_type: METHODS
|
|
section_title: "Knowledge Graph Embedding Models"
|
|
section_order: 3
|
|
|
|
- section_id: https://w3id.org/heritage/section/kg-embed-experiments
|
|
section_type: RESULTS
|
|
section_title: "Experimental Setup and Results"
|
|
section_order: 4
|
|
|
|
- section_id: https://w3id.org/heritage/section/kg-embed-discussion
|
|
section_type: DISCUSSION
|
|
section_title: "Discussion and Analysis"
|
|
section_order: 5
|
|
|
|
- section_id: https://w3id.org/heritage/section/kg-embed-conclusion
|
|
section_type: CONCLUSION
|
|
section_title: "Conclusions and Future Work"
|
|
section_order: 6
|
|
|
|
provenance:
|
|
data_source: CSV_REGISTRY
|
|
data_tier: TIER_2_VERIFIED
|
|
extraction_date: "2025-11-09T15:45:00Z"
|
|
extraction_method: "Manual curation from arXiv metadata API"
|
|
confidence_score: 0.95
|
|
|