Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
flipboard.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
Welcome to Flipboard on Mastodon. A place for our community of curators and enthusiasts to inform and inspire each other. If you'd like to join please request an invitation via the sign-up page.

Administered by:

Server stats:

1.2K
active users

flipboard.social: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.7

#OpenScience

81 posts73 participants14 posts today
Public
Holle Meding

📚 Extracting Citations with LLMs

At the #LLM for HPSS workshop, @cmboulanger David Carreto Fidalgo & Andreas Wagner presented LLaMore: a Python tool for extracting citation data from unstructured legal & humanities texts using #LLMs

Unlike GROBID, LLaMore handles complex footnotes and free-form references. Early results with GPT-4o and Llama 3.3 show significantly higher accuracy when benchmarked against a new gold standard TEI-annotated dataset.

#TEI #openscience @maxplanckgesellschaft

Comparison of citation extraction tools: While GROBID performs well on familiar structured data, LLaMore with Gemini achieves up to 3× better results on footnoted, unstructured texts.
How LLaMore works: Citation data is extracted from PDFs or raw text using LLM-based extractors and exported to TEI XML; evaluation is done via F1-score against gold standard annotations.
Public
Milano University Press

#Events

📆 Il 24 aprile alle 12.00 siete tutti invitati al webinar "Applying DOAS – insights from early adopters", in cui racconteremo la nostra esperienza, come casa editrice Diamond #OpenAccess, sull'utilizzo del Diamond Open Access Standard (#DOAS) nelle nostre #riviste

🔗 Registratevi qui diamasproject.eu/diamas-conver

📣 Saremo ospiti del #DIAMAS project, i creatori di questo nuovo standard e del Diamond Capacity Hub, ampio progetto europeo per la scienza aperta

Diamas conversation series
#OpenScience
Public
Dutch Reproducibility Network

Discussions about #OpenScience and #Reproducibility are better when a range of epistemic voices are heard.
Are you interested in openness and transparency for #qualitativeResearch methods? Then quickly sign-up for the first meeting of the European Open Qualitative #Research #Community!

Seeing this post too late (i.e. after 4th April?) - do not worry, reach out to Nicki Lisa Cole to be added to the mailing list

docs.google.com/forms/d/e/1FAI

Public
Peter Kraker

Reflecting on the 2nd Austrian Library Congress 🧠📚

As always, it was great reconnecting with colleagues and I also enjoyed the varied and high-quality programme.

A special thank you to everyone who joined my talk on AI and libraries! I'm especially inspired by the enthusiasm for @OKMaps and our organisational services, which make it easy to integrate AI-driven, visual discovery in library systems.

How do you see the role of AI in the future of libraries?

A close-up of Peter Kraker at the podium during the 2nd Austrian Library Congress. He is mid-speech, wearing a blazer, glasses, and a lanyard, standing behind a podium branded with the event's colourful logo and title.
Peter Kraker giving a presentation at the 2nd Austrian Library Congress. Behind him is a large presentation slide reading: "Did you know? Your brain can identify images seen for as little as 13 milliseconds."
A banner flag at the entrance of the 2nd Austrian Library Congress, featuring the event's name, dates (25–28 March 2025), and a colourful graphic showing iconic landmarks of Vienna.
Exterior view of the Austria Center Vienna, the modern venue hosting the 2nd Austrian Library Congress, under a partly cloudy sky.
#OpenScience#AI#Libraries
ExploreLive feeds
About