Rethinking table retrieval from data lakes
- Existing table retrieval approaches estimate each table’s relevance for a particular information need and return a ranking of the most relevant tables. This approach is not ideal since the returned tables often include irrelevant data and the required information may be scattered across multiple tables. To address these issues, we propose the idea of fine-grained structured table retrieval and present our vision of R2D2, a system which slices tables into small tiles that are later composed into a structured result that is tailored to the user-provided information need. An initial evaluation of our approach demonstrates how our idea can improve table retrieval and relevant downstream tasks such as table question answering.
Author: | Bodensohn Jan-MichaORCiDGND, Carsten BinnigORCiDGND |
---|---|
URN: | urn:nbn:de:hebis:30:3-809538 |
ISSN: | 1866-1238 |
ISSN: | 2700-2241 |
Parent Title (English): | Efl insights : an elf - the Data Science Institute publication |
Publisher: | E-Finance Lab e.V. |
Place of publication: | Frankfurt am Main |
Document Type: | Article |
Language: | English |
Date of Publication (online): | 2024/07/01 |
Date of first Publication: | 2024/07/01 |
Publishing Institution: | Universitätsbibliothek Johann Christian Senckenberg |
Release Date: | 2024/07/12 |
Volume: | 2024 |
Issue: | 2 |
Page Number: | 2 |
First Page: | 4 |
Last Page: | 5 |
HeBIS-PPN: | 521949289 |
Institutes: | Angeschlossene und kooperierende Institutionen / E-Finance Lab e.V. |
Dewey Decimal Classification: | 3 Sozialwissenschaften / 33 Wirtschaft / 330 Wirtschaft |
Sammlungen: | Universitätspublikationen |
Licence (German): | Deutsches Urheberrecht |