The automation of subject indexing and the role of metadata in times of Large Language Models

Author(s)
Keywords

subject indexing

automation

machine learning

artificial intelligen...

IT infrastructure

metadata

large language models...

neuro-symbolic integr...

Issue Date
May 15, 2024
Publisher
euroCRIS
Type
Conference Proceeding
Abstract
So far, virtually every system that facilitates access to and exploration of information resources – library catalogues, discovery systems, research information systems – has metadata as a central component. Accordingly, generating and curating high-quality metadata has always been a core activity of information infrastructure institutions, especially libraries. This includes creating or extracting semantic metadata, also called subject indexing, i.e., the enrichment of metadata records for textual resources with descriptors from a standardized, controlled vocabulary. Due to the proliferation of digital documents, it is no longer possible to annotate every single document intellectually, which generates the need to explore the potentials of automation on every level.
Description
Extended abstract presented at the CRIS2024 conference in Vienna.-- Event programme available at https://cris2024.eurocris.org/#programme
14 slides.-- Presentation delivered within Session 3.2 "New developments" on Wed May 15th, 2024
URI
https://dspacecris.eurocris.org/handle/11366/2526
DOI
File(s)
Thumbnail Image
Name

Kasprzik-CRIS2024_slides_Automation-subject-indexing.pdf

Description
Presentation (PDF)
Size

1.02 MB

Format

Adobe PDF

Checksum (MD5)

8d4fb593c22dbcc19394e00c4b840b4a

Thumbnail Image
Name

Kasprzik-CRIS2024-Automation-subject-indexing.pdf

Description
Extended abstract (PDF)
Size

124.05 KB

Format

Adobe PDF

Checksum (MD5)

35ce9a49dd74a5eabe46ec5d35b70a66