First tests with ChatGPT's GPT Builder

-

Here is a comparison of the MARC21 records in a data table format, highlighting the differences and similarities between all three versions:

FieldOriginal MARC RecordImage-Based MARC Record (2nd)Revised Image-Based Record (Resembling 1st)
1001$aLiu, Cixin,$d1963-$eauthor.1$aLiu, Cixin.1$aLiu, Cixin,$d1963-$eauthor.
240Not presentNot present10$a[Original title in Chinese].$lEnglish
24510$aTo hold up the sky /$cCixin Liu ; translated by various.10$aTo hold up the sky /$cCixin Liu.10$aTo hold up the sky /$cCixin Liu ; translated by various.
260\$a[Place of publication not identified] :$bTor, $c2020.\$bTor,$c[Date of publication not visible in the image].\$bTor,$c[Year not visible in the image].
300\$a[Number of pages] p. ;$c24 cm.\$a[Number of pages not visible]$c[Dimensions not visible].\$a[Number of pages not visible] ;$c[Size not visible] cm.
500\$aTranslation of: [Original title in Chinese].$a"Stories from the award-winning author of The Three-Body Problem and The Wandering Earth."\$aStories from the award-winning author of The Three-Body Problem and The Wandering Earth.\$aTranslation of: [Original title in Chinese].$aIncludes bibliographical references.
520Not presentNot present\$aA collection of short stories by Cixin Liu, reflecting on human nature, society, and the universe.
650\0$aScience fiction, Chinese$vTranslations into English.$aShort stories.$aHuman-alien encounters$vFiction.$aEnd of the world$vFiction.\0$aScience fiction, Chinese.$aShort stories, Chinese.\0$aScience fiction, Chinese$vTranslations into English.$aShort stories, Chinese$vTranslations into English.
655\0$aScience fiction.Not present\7$aScience fiction.$2lcgft
74002$aThe Three-Body Problem.$aThe Wandering Earth.Not present02$aThe Three-Body Problem.$aThe Wandering Earth.
020\$a9781250306081$q(hardcover)\$a9781250306081$q(hardcover)\$a9781250306081$q(hardcover)

This table illustrates the iterative process of building a MARC record. The final column reflects a more complete record by incorporating more details and MARC field indicators based on the first record and the information visible in the image. Note that some fields such as the 240 and 500 fields contain placeholder text "[Original title in Chinese]" and "[Year not visible in the image]" which would be replaced with the actual information upon verification. The 520 field, which contains the summary, is also based on the cover's description and would be adapted to match the book's content accurately.

Comments

Post a Comment

Popular posts from this blog

Switching to Local LLM Setup

-
This project isn't over, but I am looking at what it would take to set up the same "multi-modal insta-MARC" functionality with an offline setup. To me this seems like the more interesting use case. I think I've already proved that yes, adding the MARC21 rulebook in an RAG setup can produce better results, but what's the point if your Chatbot is basically doing a Bing search with ISBN numbers? Copy-cataloging has been around for a long time (and perhaps catalogers would be better suited creating custom GPTs based on their own local practices or integrating with a tool like MarcEdit ).  I'm also not seeing any librarians looking seriously at local LLMs as an option...c'mon, Chat with RTX  is right there! Mixtral ! Gemma ! Don't put all of your eggs in one basket!
Read more

The 5 Laws of Library Science but for Generative AI

-
For reference, here's a wiki about the original 5 laws proposed by S. R. Ranganathan in 1931 . And now the revision: Adaptive Purpose : AI should dynamically serve specific user needs. Inclusive Personalization : AI must cater to diverse users respectfully. Ethical Insight : AI responses should be accurate, context-aware, and ethically informed. Efficient Utility : AI must provide quick and clear answers to maximize user time. Continual Growth : AI should evolve continuously, learning from interactions and data. So I had a convo w/ GPT-4 about how to revise these and make them more concise. Weird how they almost sound like custom instructions, no? We basically have #1-4 already in place, and #5 is very close to being real w/ things like MemGPT already out there .  (I haven't read much about how memory management works w/ Generative AI but my guess is that we'll quickly need better garbage collection ...and certain apps will probably need to avoid long-term memory entirely)
Read more

Book Publishing as a "Synthetic Data" Source (with LoC as Source of Truth)

-
"Your idea of using Large Language Models (LLMs) to catalog new books and then cross-referencing this with actual cataloging done by the Library of Congress is quite innovative and could have several benefits in the realm of data management and library science. Let’s explore this idea in more detail: Automated Cataloging with LLMs : LLMs can process and understand large volumes of text efficiently. They could be trained to read new books and extract key information such as titles, authors, themes, genres, and other metadata. This could significantly speed up the cataloging process. Quality and Consistency Control : By cross-referencing with the Library of Congress catalog, which is a standard in bibliographic data, you can ensure that the data generated by the LLM is accurate and consistent with established cataloging practices. Handling Large Volumes of Books: With the sheer volume of books published every year, LLMs can provide a scalable solution to catalog new books quickly a...
Read more