The Observatoire des textes, des idées et des corpus (ObTIC) is organizing a conference on Thursday, October 21, 2021 on the theme “NLP and literary analysis: Issues, methods and new fields of investigation.”

The event will include a wide range of prominent speakers from various disciplines who will present their research projects, challenges and applications. A poster session will also be held at lunchtime. 

Program:

10h00 Welcome - Gérard Biau

10h15 Opening - Glenn Roe 

Session 1: Enriching corpora

10h30 Antoine Doucet - Université de Lorraine - NLP in the NEWSEYE project

11h00 Carmen Brando - EHESS - Named entities and beyond: challenges of machine learning based methods for computational literary analysis

11h30 Yoann Dupont, Post-doctorant, ObTIC: The Picture of Named Entity Recognition in Literature

12h00 - Lunch and poster session

• Ljudmila Petkovic - Doctorante ObTIC - State of the art in the post-OCR correction for NER
• Caroline Parfait et Jean-Baptiste Tanguy - Doctorants ObTIC-SCAI-CELLF, From the automatic creation of digital corpora to their use in the DH: a question of measurement
• Angélique Allaire - Doctorante ObTIC - Archeologists’ Tales of Travels to Greece: Uncovering the French-German Competition
• Maya Sahraoui, MNHN/LIP6, Weakly supervised named entity recognition for text to data translation in biology corpora

Session 2: New models, new methods

13h30 Chloé Ragazzoli, Sorbonne Université, Orient et Méditerranée et Serge Rosmorduc, CNAM - Solutions for identifying authors by image classification and textual criteria in Egyptology

14h00 Pierre-Carl Langlais - CELSA - NLP for the analysis of journals (tbc)

14h30 Julien Launay, Lighton - PAGnol and recent developments around very large scale models

15h00 Coffee break

Session 3: From text summarisation to text generation 

15h15 Vincent Guigue, MCF LIP6, Automatic summary, sentiment analysis

15h45 Thierry Poibeau - LATTICE -  Automatic translation, automatic generation

16h15 Discussion

16h30 End

 

The Observatoire des textes, des idées et des corpus (ObTIC), SCAI's project-team dedicated to digital humanities, draws on an established expertise in the domain of digital editions, data exploration and production for humanities research. ObTIC team members are actively involved in the design and application of software and algorithms for humanities researchers, as well as the development and evaluation of new digital research methodologies across these same fields of inquiry.

ObTIC’S specificity: opening up traditional humanities disciplines to digital methodologies by approaching texts and corpora through transversal concepts independent of any particular textual genre.