Programme (NEW)

CONFERENCE PROGRAME (Updated 23/9/2020)

All times are based on the Eastern European Time (EEST). Please pay attention if you live in another time zone.

Monday, 21 September, 2020

13:00-17:00 Pre-conference event: European Language Grid Roadshow: Workshop of Baltic Countries

Tuesday, 22 September, 2020

9:00 Conference opening

9:20-10:20 Invited speech: Daniel Zeman Universal Dependencies: A Search for Harmonized Morphological and Syntactic Annotation

10:20-10:50 Coffee break

Session 1: Speech and Text Analysis

Chair: Mārcis Pinnis

10:50-11:10 A Study in Estonian Pronominal Coreference Resolution

Eduard Barbu, Kadri Muischnek and Linda Freienthal

11:10-11:30 Using Privacy-Transformed Speech in the Automatic Speech Recognition Acoustic Model Training

Askars Salimbajevs

11:30-11:50 Evaluating Multilingual BERT for Estonian

Claudia Kittask, Kirill Milintsevich and Kairit Sirts

11:50-12:10 LVBERT: Transformer-based Model for Latvian Language Understanding

Artūrs Znotiņš and Guntis Bārzdiņš

12:10-12:30 Large Language Models for Latvian Named Entity Recognition

Rinalds Vīksna and Inguna Skadiņa

12:30-13:30 Lunch

Session 2: Machine Translation and Natural Language Understanding

Chair: Eduard Barbu

13:30-13:50 Data Augmentation for Pipeline-Based Speech Translation

Diego Alves, Askars Salimbajevs and Mārcis Pinnis

13:50-14:10 Robust Neural Machine Translation: Modeling Orthographic and Interpunctual Variation

Toms Bergmanis, Artūrs Stafanovičs and Mārcis Pinnis

14:10-14:30 Intent Detection-based Lithuanian Chatbot Created via Automatic DNN Hyper-Parameter Optimization

Jurgita Kapočiūtė-Dzikienė

14:30:14:50 Towards Hybrid Model for Human-computer Interaction in Latvian

Inguna Skadiņa and Didzis Goško

14:50-15:30 Coffee break

15:30-16:30 Virtual poster session 1

  1. Loïc Boizou and William Lamb An Online Linguistic Analyser for Scottish Gaelic
  2. Virginijus Dadurkevičius and Rūta Petrauskaitė Corpus-based Methods for Assessment of Traditional Dictionaries
  3. Daiga Deksne and Raivis Skadiņš Interactive Learning of Dialog Scenarios from Examples
  4. Sigita Dereškevičiūtė and Asta Kazlauskienė Structural Models of Lithuanian Plosive Consonants in Different Word Positions
  5. Justina Mandravickaitė and Tomas Krilavičius Similarities and Differences of Lithuanian Functional Styles: a Quantitative Perspective
  6. Mažvydas Petkevičius, Daiva Vitkutė-Adžgauskienė and Darius Amilevičius Targeted Aspect-Based Sentiment Analysis for Lithuanian Social Media Reviews
  7. Andrius Utka, Jurgita Vaičenonienė, Monika Briedienė and Tomas Krilavičius Development and Research in Lithuanian Language Technologies (2016-2020)
  8. Gaurish Thakkar and Mārcis Pinnis Pretraining and Fine-Tuning Strategies for Sentiment Analysis of Latvian Tweets

Wednesday, 23 September, 2020

Session 3: Language Learning Resources

Chair: Jurgita Vaičenonienė

09:00-10:00 Invited speech: Elena Volodina Learner Corpora – Overcoming Challenges with Building and Sharing the Data

10:00-10:20 Detailed Error Annotation for Morphologically Rich Languages – Latvian Use Case

Roberts Darģis, Ilze Auziņa, Kristīne Levāne-Petrova and Inga Kaija

10:20-10:40 Error Tagging in the Lithuanian Learner Corpus

Jūrate Ruzaitė, Sigita Dereškevičiūtė, Viktorija Kavaliauskaitė-Vilkinienė and Eglė Krivickaitė-Leišienė

10:40-11:00 Coffee break

Session 4: Tools and Resources

Chair: Inguna Skadiņa

11:00-11:20 Creation of Language Resources for the Development of a Medical Speech Recognition System for Latvian

Roberts Darģis, Normunds Grūzītis, Ilze Auziņa and Kaspars Stepanovs

11:20-11:40 Adding Compound Splitting and Analysis to a Semantic Tagger of Modern Standard Finnish – on the Way to FiSTComp

Kimmo Kettunen

11:40-12:00 Language Technology Platform for Public Administration

Raivis Skadiņš, Mārcis Pinnis, Artūrs Vasiļevskis, Andrejs Vasiļjevs, Valters Šics, Roberts Rozis and Andis Lagzdiņš

12:00-12:20 Morfio – a Corpus-based Perspective on Latvian Morphology

Michal Škrabal, Pavel Vondřička and Václav Cvrček

12:20-12:40 Lexicon-Enhanced Neural Lemmatization for Estonian

Kirill Milintsevich and Kairit Sirts

12:40-13:00 Evaluating Sentence Segmentation and Word Tokenization Systems on Estonian Web Texts

Kairit Sirts and Kairit Peekman

13:00-14:00 Lunch break

14:00-15.00 Invited speech: Jan Rybicki Books and Computers, Books in Computers: Stylometry in Literary Originals and Translations

15:00-15:30 Coffee break

15:30-16:30 Virtual poster session 2

  1. Roberts Darģis, Kristīne Levāne-Petrova and Ilmārs Poikāns Lessons Learned from Creating a Balanced Corpus from Online Data
  2. Daiga Deksne and Anna Vulāne Towards the Development of Language Analysis Tools for the Written Latgalian Language
  3. Hugo Sanjurjo-González Berri Corpus Manager: A Corpus Analysis Tool Using MongoDB Technology
  4. Uga Sproģis and Matīss Rikters What Can We Learn From Almost a Decade of Food Tweets
  5. Laine Strankale and Pēteris Paikens OCR Challenges for a Latvian Pronunciation Dictionary
  6. Aivaras Rokas, Sigita Rackevičienė and Andrius Utka Automatic Extraction of Lithuanian Cybersecurity Terms Using Deep Learning Approaches
  7. Ingrida Balčiūnienė and Aleksandr N. Kornev Quantitative Analysis of Language Competence vs. Performance in Russian- and Lithuanian-speaking 6 Year-olds
  8. Loïc Boizou, Jolanta Kovalevskaitė and Erika Rimkutė Lithuanian Pedagogic Corpus: Correlations between Linguistic Features and Text Complexity
  9. Jolanta Kovalevskaitė, Agnė Bielinskienė, Loïc Boizou, Laima Jancaitė and Erika Rimkutė The First Corpus-driven Lexical Database of Lithuanian as L2

16:30-16:40 Conference closing