Abstract
This paper presents a new methodology for AI-based research and exploration of large genealogical corpora. The proposed approach is based on an automatic quantitative question-answering (QA) system that enables researchers to ask questions in natural language and learn about trends related to individuals, families, and communities in the corpus of the study. The proposed methodology includes: 1) an automatic method for training dataset generation, 2) a transformer-based table selection method, and 3) an optimized transformer-based quantitative QA model. The findings indicate that the proposed architecture outperforms the state-of-the-art models by achieving 87% accuracy on the large corpus of Jewish genealogical data. This study may have practical implications for genealogical information centers and museums, making genealogical data research easy and scalable for experts as well as the general public.
| Original language | English |
|---|---|
| Pages (from-to) | 733-737 |
| Number of pages | 5 |
| Journal | Proceedings of the Association for Information Science and Technology |
| Volume | 60 |
| Issue number | 1 |
| DOIs | |
| State | Published - Oct 2023 |
Bibliographical note
Publisher Copyright:86 Annual Meeting of the Association for Information Science & Technology | Oct. 27 – 31, 2023 | London, United Kingdom. Author(s) retain copyright, but ASIS&T receives an exclusive publication license.
Keywords
- Question-answering
- cultural heritage
- deep learning
- digital humanities
- genealogical data