invites you to the

Workshop on Deep Learning and Neural Approaches for Linguistic Data

Skopje, North Macedonia & online

30 September 2021

Proceedings are available in the Book of Abstracts

Programme (times in CEST):

  • 8:30 – 10:00 presentations:
    • D. Gromann, L. Wachowiak, C. Lang, B. Heinisch: Multilingual Extraction of Terminological Concept Systems
    • G. Valūnaitė Oleškevičienė, C. Liebeskind, D. Trajanov, P. Silvano, C. Chiarcos, M. Damova: Speaker Attitudes Detection through Discourse Markers Analysis
    • H. G. Oliveira: Acquiring Lexico-Semantic Knowledge from a Portuguese Masked Language Model
    • V. Păiș, M. Mitrofan: Towards a named entity recognition system in the Romanian legal domain using a linked open data corpus
    • M. Susman, D. Leijen, N. Groom, C. Johansson: Investigating Academic Document Structure using Object Detection Methods
  • 10:00 – 10:30 (virtual) coffee break
  • 10:30 – 11:00 panel discussion: Jorge Gracia, Mariana Damova, Dagmar Gromann, Hugo Gonçalo Oliveira, Andrius Utka, Marko Robnik-Šikonja, Dimitar Trajanov, Christer Johansson, Radovan Garabík

Scientific committee:

  • Eliot Bytyçi, University of Prishtina
  • Radovan Garabík, Ľ. Štúr Institute of Linguistics, Slovak Academy of Sciences
  • Hugo Gonçalo Oliveira, University of Coimbra
  • Dagmar Gromann, University of Vienna
  • Chaya Liebeskind, Jerusalem College of Technology, Lev Academic Center
  • Purificação Silvano, University of Porto
  • Giedrė Valūnaitė Oleškevičienė, Mykolas Romeris University

Deep learning and neural network approaches are indispensable in modern Natural Language Processing and generally in all kinds of linguistic data analysis approaches. The workshop is aimed at deep learning in connection with linguistic data and the effective use of deep learning in understanding the specificities of linguistic data, to be better exploited and combined with linked data mechanisms. Researchers from all areas of NLP, corpus and computational linguistics are invited to present their research, results, tools and applications. Presenting ongoing research, projects, work in progress and future plans is welcome, as well as notable already published results.

We are especially interested in, but do not restrict the workshop to, topics, such as:

  • Language models for the Multilingual Semantic Web,
  • Enhancement of language models with structured linguistic data,
  • Neural Machine Translation for LLOD interlinking,
  • Structured linguistic data to improve Neural Machine Translation,
  • Use cases combining language models and structured linguistic data

Selection process: Submissions will be reviewed based on their suitability for the overall topic and their potential contribution to the discussion of the workshop. Submissions are going to be included in an online booklet of abstracts.

Mode of presentation: hybrid - both physical and online.
Location: Skopje, North Macedonia
Submission deadline: 30 June 15 July 2021
Notification deadline: 2 August 2021
Online booklet publication: 15 September 2021
Workshop: 30 September 2021
Submission type: extended abstracts
Length: max. 2 pages including references
Format: Springer Lecture Notes in Computer Science (LNCS); LaTeX, Overleaf, MS Word or plain text
Registration and participation: free of charge
Submission page:
E-mail contact:

Supported by CA18209 – European network for Web-centred linguistic data science