Skip to end of banner
Go to start of banner

LLM Assisted MARC Management

Skip to end of metadata
Go to start of metadata

You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 5 Next »

MARC Fields Range

Extraction

Generation

Evaluation

00X: Control Fields

01X-09X: Numbers and Code Fields

  • 041 Language Code

automation via python script - done

converting to code isn’t done

1XX: Main Entry Fields

20X-24X: Title and Title-Related Fields

25X-28X: Edition, Imprint, Etc. Fields

3XX: Physical Description, Etc. Fields

4XX: Series Statement Fields

5XX: Note Fields

  • 504 - Bibliography, Etc. Note

Biliography/discography section could be located by LLM. could be prototyped

  • 520: Summary, etc.

automation via python script - done

manual gpt test done - comparison against reference value from existing MARC

6XX: Subject Access Fields

  • 650 - Subject Added Entry - Topical Term

automation via python script - done

verification against LC vocabulary is not done

70X-75X: Added Entry Fields

76X-78X: Linking Entry and Description Fields

80X-83X: Series Added Entry Fields

841-88X: Holdings, Location, Alternate Graphics, Etc. Fields

Definitions:

  • Extraction - finding the value inside the catalogued instance and copying it as is.

    • Example: a book may be written in English and yet may not contain the word “English” at all, so defining the book’s language would be generation rather than extraction

    • Example: An abstract could both be generated or extracted, the latter is possible for a scientific articles which often contain abstracts

  • Generation - producing the value which might not be found inside the catalogued instance

  • Evaluation - measuring qualities of the value, which is either generated/extracted or existing or obtained with some other tools

  • No labels