OAEI Machine Learning Dataset for Online Model Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916227813736448 |
|---|---|
| author | Hertling, Sven Norouzi, Ebrahim Sack, Harald |
| author_facet | Hertling, Sven Norouzi, Ebrahim Sack, Harald |
| contents | Ontology and knowledge graph matching systems are evaluated annually by the Ontology Alignment Evaluation Initiative (OAEI). More and more systems use machine learning-based approaches, including large language models. The training and validation datasets are usually determined by the system developer and often a subset of the reference alignments are used. This sampling is against the OAEI rules and makes a fair comparison impossible. Furthermore, those models are trained offline (a trained and optimized model is packaged into the matcher) and therefore the systems are specifically trained for those tasks. In this paper, we introduce a dataset that contains training, validation, and test sets for most of the OAEI tracks. Thus, online model learning (the systems must adapt to the given input alignment without human intervention) is made possible to enable a fair comparison for ML-based systems. We showcase the usefulness of the dataset by fine-tuning the confidence thresholds of popular systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_18542 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | OAEI Machine Learning Dataset for Online Model Generation Hertling, Sven Norouzi, Ebrahim Sack, Harald Information Retrieval Ontology and knowledge graph matching systems are evaluated annually by the Ontology Alignment Evaluation Initiative (OAEI). More and more systems use machine learning-based approaches, including large language models. The training and validation datasets are usually determined by the system developer and often a subset of the reference alignments are used. This sampling is against the OAEI rules and makes a fair comparison impossible. Furthermore, those models are trained offline (a trained and optimized model is packaged into the matcher) and therefore the systems are specifically trained for those tasks. In this paper, we introduce a dataset that contains training, validation, and test sets for most of the OAEI tracks. Thus, online model learning (the systems must adapt to the given input alignment without human intervention) is made possible to enable a fair comparison for ML-based systems. We showcase the usefulness of the dataset by fine-tuning the confidence thresholds of popular systems. |
| title | OAEI Machine Learning Dataset for Online Model Generation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2404.18542 |