I've noticed that you can ask #LLMs (I tried with Bing and Bard) to evaluate if two research papers are in agreement or not. In my limited testing it has been quite reliable and this gave me the idea of using LLMs to build signed #bibliographic #networks. But I know I'll never have the time / energy to do that .. so please go ahead.

Question for he #LIS #library folks on here: I'm looking for a simple way to embed #bibliographic #metadata into an #HTML page for consumption by tools like #Zotero. #CoinS / #OpenURL / #Z39_88 seems to be an option and it does work. But there appears to be no field for the #editor(s) of a #book and I'm having troubles with the #DOI. Documentation seems hard to find -- this seemed useful, but limited: https://web.archive.org/web/20140922055507/http://ocoins.info/cobgbook.html. – Where should I look? Or are there better alternatives to #CoinS?

@sarahjamielewis It is not only about proprietary data. Still the most compatible format for the most data-modelled possible, #bibliographic databases, is #BibTeX which nobidy would ever suspected was meant seriously as a data format.

All #bibliographic tools I know (#Zotero, Papers, #CiteULike, etc.) do a terrible job with accents/umlauts and need to be hand corrected and I suspect this one is no different. However, it usually takes a few clicks on a journal webpage to get a #BibTeX entry. This program is at least as convenient and lends itself to automation.

Has anyone used large language models for extracting (#bibliographic style, e.g. #DublinCore) #metadata from fulltext (PDF) documents? I tried this with a fine-tuned #OpenAI #GPT3 Curie model and the results were outrageously good at least for doctoral theses. Much better than traditional NLP methods like #GROBID.

#AI #machinelearning #LLM

This #bookish #ChristmasCard has a personal connection. It comes from our late University of Massachusetts colleague Arthur F. Kinney: prolific scholar of English literature, friend & mentor. In 1998, he founded the University of Massachusetts Renaissance Center that now bears his name
(https://www.umass.edu/news/article/memoriam-arthur-f-kinney#:~:text=Share%20This-,Arthur%20F.,2016%20as%20the%20Thomas%20W)

Arthur loved Christmas & each year sent friends a card employing image & text from a #medieval or #Renaissance book--with proper #bibliographic description, of course

@bookstodons 3/n

Can anyone help me? How do you give a #bibliographic #citation to pieces in the anthropological newsletter #SAPIENS?

RT @zfrancophone

Utilisateurs #Android + #zotero : des retours sont les bienvenus sur vos applications préférées, trucs et astuces ! 👇
#bibliographic #academics #outils #tools #softwares #apps https://twitter.com/dbelveze/status/1590250092816211968

🐦🔗: https://twitter.com/zfrancophone/status/1590343923868000256

RT @zfrancophone

Utilisateurs #Android + #zotero : des retours sont les bienvenus sur vos applications préférées, trucs et astuces ! 👇
#bibliographic #academics #outils #tools #softwares #apps https://twitter.com/dbelveze/status/1590250092816211968

🐦🔗: https://twitter.com/zfrancophone/status/1590343923868000256

D-9 for our first #InventaireOpenWeek https://wiki.inventaire.io/wiki/Inventaire-OpenData-Week-2019 join us if you're around Central Europe!
#inventaireio #wikidata #bibliographic #opendata #LOD