davidlassner retweeted
Our Humanistic NLP dream team from left to right: @davidlassner @apjanco, moi, Natasha Ermolaev (locked out of Twitter — apparently “a long story” 😀) & @thatbudakguy. We loved presenting our @DARIAHeu + @PrincetonDH collab at the #DH2023 Language Models sessions earlier today. – at Graz, Austria
davidlassner retweeted
Now online 😍 ! My book "From Handwriting to Footprinting: Text and Heritage in the Age of Climate Crisis" is now published and can be downloaded at: openbookpublishers.com/books…
davidlassner retweeted
Woooo! 😳 Our #DraCor team just won the 2022 #Rahtz Prize for #TEI Ingenuity. What! An! Honor! Thanks to @TEIconsortium – and thanks to all the "DraCorians" out there.
🏆And the winner of the 2022 Rahtz Prize for #TEI Ingenuity is:
🏅DraCor – Drama Corpora Project: dracor.org/.
davidlassner retweeted
📢to all historians looking for digital tools to analyze historical sources: CorDeep, a #ML based web application, is able to extract 4 different classes of visual elements within historical sources from the 15th to the 17th centuries. 👉bifold.berlin/news-events/ne…
davidlassner retweeted
I am delighted to share that "Domain-Specific Word Embeddings with Structure Prediction" has been accepted to TACL. This is joint work with @davidlassner @AnneBaillot & Shin Nakajima @coastalcph & @bifoldberlin. Preprint here: arxiv.org/abs/2210.04962. Code follows soon! TL;DR:
davidlassner retweeted
📝 Preprint is now online at arxiv.org/abs/2210.04963
👩💻 Code here: github.com/stephaniebrandl/e…
Happy to share that our paper "Every word counts: A multilingual analysis of individual human alignment
with model attention" together with @norahollenstein has been accepted to AACL-IJCNLP @coastalcph @CST_UCPH. Preprint follows soon, for now TL;DR:
Just saw that @stjoweil uploaded a kraken model for German fraktur. I just want to thank you! Are compatible with eScriptorium and have a very solid recognition without any fine tuning on my documents. It will be a jump start for fraktur projects that rely on a free OCR pipeline.
davidlassner retweeted
The Sphere project is an incubator of multiple #Digital #Humanities (DH) approaches. Want to learn more about the evolution and transmission of knowledge in the early modern period? 👉bifold.berlin/homogenization…
davidlassner retweeted
We invite the TEI community to nominate prospective candidates for the Rahtz Prize for TEI Ingenuity 2022: rb.gy/ynxxk4.
Nominations and self-submissions should only be submitted through this form: rb.gy/xcmoe6.
Deadline: 30 June 2022 by midnight (HAST).
davidlassner retweeted
May 11–12: Join us for the New Languages for NLP: Building Linguistic Diversity in the Digital Humanities Conference feat. participants from the @nlp_new Institute and keynotes by David Bamman and Ines Montani. In person and online. Open to all. Sign up! cdh.princeton.edu/updates/20…
![A poster for the New Languages for NLP conference with a yellow, green, and pink pattern and white text. The poster reads: "New Languages for NLP: Building Linguistic Diversity in the Digital Humanities Conference. Participants from the Center for Digital Humanities New Languages for NLP Institute will share results, challenges and lessons learned while spending a year learning how to create linguistic data and training NLP models for under-resourced languages." On the left are the participants: Ephraim Berkovitch, Maroussia Bednarkiewicz, Katherine Bowers, Nick Budak, Cameron Gibson, John Hale, Kate Holland, Alíz Horváth, Chad Howe, Utitofon Inyang, Jajwalya Karajgikar, Irene Kirchner, Temitayo Olatoye, Aidan Malanoski, Gian Rominger, Sinai Rusinek, Romain Thurin. On the right are the details: May 11–12, Panels will take place at the CDH on B Floor of Firestone Library and on Zoom. Provided toward the bottom: newnlp.princeton.edu. To register: scan [QR code]or visit cdh.princeton.edu.](https://pbs.twimg.com/media/FRt0tyTWUAAf0LT.jpg?name=orig)
ALT A poster for the New Languages for NLP conference with a yellow, green, and pink pattern and white text. The poster reads: "New Languages for NLP: Building Linguistic Diversity in the Digital Humanities Conference. Participants from the Center for Digital Humanities New Languages for NLP Institute will share results, challenges and lessons learned while spending a year learning how to create linguistic data and training NLP models for under-resourced languages." On the left are the participants: Ephraim Berkovitch, Maroussia Bednarkiewicz, Katherine Bowers, Nick Budak, Cameron Gibson, John Hale, Kate Holland, Alíz Horváth, Chad Howe, Utitofon Inyang, Jajwalya Karajgikar, Irene Kirchner, Temitayo Olatoye, Aidan Malanoski, Gian Rominger, Sinai Rusinek, Romain Thurin. On the right are the details: May 11–12, Panels will take place at the CDH on B Floor of Firestone Library and on Zoom. Provided toward the bottom: newnlp.princeton.edu. To register: scan [QR code]or visit cdh.princeton.edu.
That moment where you look at the results of last night's model training on a new data set and, in shock, realise you must have screwed up your data preparation - why is my PhD supervisor a label in my dataset? @AnneBaillot (turns out gutenberg.org/files/53490/53…)
davidlassner retweeted
We are thrilled to be hosting @davidlassner (@TUBerlin+@bifoldberlin) for an online seminar on “Translatorship attribution with strong confounders & how to make friends between TEI and NLP” on the 4th Feb 2022, 11am CET. See almanach.inria.fr/seminars-e…. Link to be shared on the day!
davidlassner retweeted
Finishing up our second New Languages for NLP workshop. Totally zoomed out, but it was a really fun week. Still hoping to meet in person at Princeton in May. Thanks, everybody. See you again at our next monthly check-in. @nlp_new @PrincetonDH @DARIAHeu newnlp.princeton.edu
This was such a fun project! Among other things, we surveyed cultural heritage institutions with data republication requests (that we considered Public Domain) and, honestly, we were not prepared for the diversity of responses 😅
Es gibt einen neuen Artikel aus #vDHdPub: "Publishing an OCR ground truth data set for reuse in an unclear copyright setting" von @davidlassner, Julius Coburger, @cneudecker und @AnneBaillot.
zfdg.de/sb005_006
@MelusinaPress @vDHd2021 @MWWForschung
davidlassner retweeted
The "Brace your digital edition" work session on November 19th, feat. @davidlassner @laurentromary @MissBrutus @Alix_Tz @HugoSchtr @StephanieBrandl @AnnaArchiv @sabine_seifert @torstenroeder, is hosted by @bifoldberlin - a huge thanks to them for making this meeting possible!
davidlassner retweeted
Ich freue mich, dass unser Workshop “Textexplorationen in der digitalen Literaturwissenschaft” mit @AnneBaillot & @davidlassner bei der @dhd2022 angenommen wurde. Auf dass die Diskussionen ähnlich anregend werden wie beim letzten Mal. Wir sehen uns in Potsdam 💜Mehr Details bald!
davidlassner retweeted
Oct 26, 4:30 pm (Zoom)!
“Machine Predictions & Synthetic Text: A Roundtable on Large Language Models in the Humanities,” featuring Angelina McMillan-Major, Margaret Mitchell, @gimenadelr, @laurenfklein, @Ted_Underwood, @ttasovac
Learn more and register: cdh.princeton.edu/updates/20…
ALT Yellow poster shows a parrot made out of gears. Information on the event "Machine Predictions and Synthetic Text: A Roundtable on Large Language Models in the Humanities" is provided.
At the #DARIAH2021 event @mellymeldubs just mentioned the idea of characterization of languages in order to have fewer NLP "pathways" that can be adapted. Are there already ressources that give an overview of such characterizations for different languages?