Natural Language Processing and Digital Humanities have evolved as two different communities with their own methodologies, standards and venues. While they share objects and sometimes even research questions, making it right for both communities remains a challenge for scholars, especially for young scholars whose research is positioned at the interface of both disciplines. The emphasis on large textual corpora as a key factor for the successful development of DH methods has brought both worlds one step closer to one another, but the interaction between them is still limited.
The goal of this event is to gather PhD candidates whose research explores or applies methods relevant for NLP as well as for DH at large (including such areas as Heritage Research or Computational Literary Studies) in order to foster dialogue and enrich approaches. Since the research communities are also strongly rooted in national structures, another goal of this event is to bring PhD candidates from a range of European scholarly cultures together.
This event is relevant for you if:
You are just starting your PhD with a strong NLP and/or DH component and wish to interact with other PhD candidates working similarly
You are in the midst of an NLP or DH PhD and realized the other field’s methods and questions might be really interesting
You really are interested in the methodological intersection of both fields
Your PhD is almost finished and presents a synthesis of both fields (or tries to)
You would be interested to hear what the other discipline makes of your corpus, methods and/or results
Program
Tuesday, 21 June 2022
Presentations of 30 minutes, followed each by a 30 minutes discussion.
8:45
Welcome
9:00: Alice Brenon, "The boring (?) details"
10:00: Gaël Poux-Médard, "Interactions in information spread"
11:00 : Caroline Koudoro-Parfait, "Spatial Named Entities Recognition in Literary Texts: the Crossroads of Digital Humanities and Natural Language Processing"
12:00-14:00 Lunch break
14:00: Alix Chagué, "Challenges in pooling training data for handwritten text recognition"
15:00: Louise Tarrade, "Detecting lexical innovations on Twitter and understand what conditions their success or failure: a computational approach"
16:00: David Lassner, "Translatorship Attribution with Confounding Author Signals"
Wednesday, 22 June 2022
9:30 : Jean-Baptiste Chaudron, "The specificities of Wikipedia's encyclopedic genre"
10:30: Floriane Chiffoleau, "The Making of Text. Optical Script Recogntion and Textual Heritage"