How to Turn Card Catalogs into LLM Fodder

Mary Ann Tan, Shufan Jiang, Harald Sack


Abstract
Bibliographical metadata collections describing pre-modern objects suffer from incompleteness and inaccuracies. This hampers the identification of literary works. In addition, titles often contain voluminous descriptive texts that do not adhere to contemporary title conventions. This paper explores several NLP approaches where greater textual length in titles is leveraged to enhance descriptive information.
Anthology ID:
2024.dlnld-1.5
Volume:
Proceedings of the Workshop on Deep Learning and Linked Data (DLnLD) @ LREC-COLING 2024
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Gilles Sérasset, Hugo Gonçalo Oliveira, Giedre Valunaite Oleskeviciene
Venues:
DLnLD | WS
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
53–65
Language:
URL:
https://aclanthology.org/2024.dlnld-1.5
DOI:
Bibkey:
Cite (ACL):
Mary Ann Tan, Shufan Jiang, and Harald Sack. 2024. How to Turn Card Catalogs into LLM Fodder. In Proceedings of the Workshop on Deep Learning and Linked Data (DLnLD) @ LREC-COLING 2024, pages 53–65, Torino, Italia. ELRA and ICCL.
Cite (Informal):
How to Turn Card Catalogs into LLM Fodder (Tan et al., DLnLD-WS 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2024.dlnld-1.5.pdf