Conference Program

Venue: Academy of Sciences of Moldova, Vladimir Andrunachievici Institute of Mathematics and Computer Science with a permanently open online session via Zoom meeting:

10 November – ConsILR Day I (all hours are EET = CET+1)

8:30 – 9:00 Connections
9:00 – 9:20 Welcome message
9:20 – 10:10 Keynote speech session 1 – chaired by Svetlana Cojocaru
          Mariia Shvedova: Regional Annotation within GRAC, a Large Reference Corpus of Ukrainian
 Abstract Slides Video

Session 1: Corpora Creation and Annotation
– chaired by Diana Trandabăț
10:10 – 10:30 Daria Costea, Andrei Moldovan and Vasile Păiș: Fine-Grained Legal References in the LegalNERo Corpus
10:30 – 10:50 Andrei-Marius Avram, Vasile Păiș and Dan Tufiș: Terminology Annotation Using a String-Matching Algorithm
10:50 – 11:10 Solomiya Buk: Dialogicity Index in the Description of the Fiction Texts

11:10 – 11:40 Coffee break
11:40 – 12:30 Keynote speech session 2 – chaired by Victoria Bobicev
        Ruslan Mitkov: With a little help from NLP: My Language Technology applications with impact on society
                                                                                          Bio Abstract

Session 2: Language Processing Tools – chaired by Vasile Păiș
12:30 – 12:50 Georgiana Druță, Adrian Iftene and Daniela Dănciulescu: Correcting Postal Addresses Written in Any Language

12:50 – 13:10 Radu Ciora and Daniela Gîfu: AI Based Solutions for Text Language Identification
13:10 – 13:30 Bianca Ionela Stratianu and Adrian Iftene: Personality Prediction Based on Social Media Posts
13:30 – 13:50 Roxana Micu, Carol Luca Gasan and Vasile Păiș: Splitting Hashtags in Romanian Micro-Blogging Texts

13:50 – 15:20 Lunch break
15:20 – 16:10 Keynote speech session 3 – chaired by Adrian Iftene
          Maciej Ogrodniczuk: ParlaMint: Multilingual Comparable Corpora of Parliamentary Debates
Bio Abstract Slides Video

16:10 – 17:00 Keynote speech session 4 – chaired by Dan Tufiș
          Christiane D. Fellbaum: Scales in the Lexicon: Identification, Construction, Applications
                        (Joint work with Vera Sheinman, Isaac Julien, Yannick Mathieu and Pulkit Singh)
                                                                                     Bio Abstract Slides Video
17:00 – 17:20 Coffee break
Session 3: Romanian Linguistic Resources – chaired by Tudor Bumbu
17:20 – 17:40 Silviu Ioan Bejinariu, Ramona Luca, Florin Iftene, Manuela Nevaci, Carmen Irina Floarea and
              Nicolae Saramandu: GIS-Based Publishing System for the Romanian Linguistic Atlas by Regions – Synthesis
17:40 – 18:00 Anca Diana Bibiri, Maria Moruz and Mihai Alex Moruz: ParemCor – Contemporary Romanian
                         Language Corpus of Proverbs and Anti-proverbs
18:00 – 18:20 Rareș Arvinte and Diana Trandabăț: Medical Corpus in Romanian Hospitals


11 November – ConsILR Day II & DeLORo workshop

8:30 – 9:00 Connections
Session 4: Digital Heritage – chaired by Isabelle Tamba

9:00 – 9:20 Dan Cristea, Petru Rebeja and Constantin Cristian Pădurariu: Applying
                          YOLOv5 Learning in Detecting Old Cyrillic-Romanian Characters
       Also part of the‎    
  ‎DeLORo workshop

9:20 – 9:40 Mihai Alex Moruz, Ana-Maria Gînsac and Mădălina Ungureanu: The Recurrence of the 16th Century
                      Romanian Psalters Vocabulary in the 17th Century Romanian Lexicons Based on Automatic Corpora Comparison
9:40 – 10:00 Eugenia Mincu: The Valorisation of Philological Resources in the Online Environment
10:00 – 10:20 Mihai Alex Moruz and Mădălina Ungureanu: The First Slavonic-Romanian Lexicons (17th Century):
                          A Digital Comparative Edition and How to Use It

10:20 – 10:50 Coffee break
10:50 – 11:40 Keynote speech session 5 – chaired by Diana Trandabăț
          Constantin Orăsan: What machine translation tells us about sentiments in other languages
                                                                               Bio Abstract Slides Video

Session 5: Semantics and Pragmatics – chaired by Victoria Bobicev
11:40 – 12:00 Julia Rogushina: Ontological Structuring of Natural Language Content in Encyclopedic Wiki-Portals
                         as a Basis for Semantic Search
12:00 – 12:20 Alexandr Parahonco and Mircea Petic: How to Create an Adaptive eLearning System

12:20 – 14:00 Lunch break
14:00 – 14:50 Keynote speech session 6 – chaired by Mircea Petic

          Svetlana Cojocaru: HeDy – a platform for heterogeneous document processing
(Joint work with Tudor Bumbu, Lyudmila Burtseva, Alexandru Colesnicov and  Ludmila Malahov)
                                                                             Bio Abstract Slides Video
    Also part of the‎    
  ‎DeLORo workshop

DeLORo workshop
– chaired by Dan Cristea
14:50 – 15:10 Roxana Vieru: An Integrating View Over Old Romanian as Digital Resources
15:10 – 15:30 Gabriela Haja, Isabelle Tamba and Andrei Scutelnicu: Could DeLORo be Linked with eDTLR and CLRE?

15:30 – 15:50 Coffee break
15:50 – 16:10 Petru Rebeja: Models for Character Recognition in DeLORo. Results and perspectives
16:10 – 16:30 Marius Popescu: N-gram models for lemmatising the old Romanian language
16:30 – 16:50 Dan Cristea: Why DeLORo Cannot Stop Here?
16:50 Closing