The New Languages for NLP: Building Linguistic Diversity in the Digital Humanities Conference is organised on May 11-12 as part of the New Languages for NLP Institute.
The conference is hosted by the Center for Digital Humanities at Princeton University in partnership with DARIAH-EU, and with generous support from a grant from the National Endowment for the Humanities.
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.
Registration is required for both in-person and Zoom participation.
Wednesday, May 11
1:00-2:30 pm EDT. Challenges in the Development of NLP Resources for New Languages: Case Studies from Kannada, Quechua, and Russian (panel)
- Speakers: Katherine Bowers (University of British Columbia), John Hale (University of Georgia), Kate Holland (University of Toronto), Chad Howe (University of Georgia), and Jajwalya Karajgikar (University of Pennsylvania)
- In-person registration or Zoom registration
2:45-4:15 pm EDT. Right to Left and Back: NLP for Ottoman Turkish, Yiddish and Classical Arabic (panel)
- Speakers: Ephraim Berkovitch (ZipRecruiter), Maroussia Bednarkiewicz (Eberhard Karls Universität), Irene Kirchner (Georgetown University), Sinai Rusinek (University of Haifa), and Romain Thurin (University of Notre Dame)
- Moderator: Christiane Fellbaum (Princeton University)
- In-person registration or Zoom registration
4:30-6:00 pm EDT. David Bamman (UC-Berkeley), “Representation in Literary NLP” (keynote)
- Live-streamed. No registration required
- Julis Romo Rabinowitz Building 399
Thursday, May 12
1:00-2:30 pm EDT. Creating Annotated Corpora for Yoruba, Efik and Tigrinya (panel; Institute participants only)
- Speakers: Cameron Gibson (CUNY Graduate Center), Utitofon Inyang (UC-Riverside), Temitayo Olatoye (University of Eastern Finland), and Aidan Malanoski (CUNY Graduate Center)
2:45-4:00 pm EDT. East Asian Historical Language Models: Beyond the Mainstream (panel)
- Speakers: Nick Budak (Stanford University), Alíz Horváth (Eötvös Loránd University), Gian Rominger (Princeton University)
- Moderator: Anna Shields (Princeton University)
- In-person registration or Zoom registration
4:30-6:00 pm EDT. Ines Montani (Explosion AI), “Solutions for Advanced NLP for Diverse Languages” (keynote)
- Live-streamed. No registration required
- Computer Science Building 104
Read more on this partnership between DARIAH-EU with Princeton University to deliver NLP Training for Humanists here.
