Programme

Tentative schedule

Note that we are building the schedule, there might be slight changes in the following weeks.

  Monday 23 Tuesday 24 Wednesday 25 Thursday 26 Friday 27
Registration          

Session 1

09.00-10.30

  

Oral presentations 1

Invited speaker:

José Camacho Collados

Oral presentations 4

 Oral presentations 6 Oral presentations 9

Coffee break

10.30-11.00

   Coffee break Coffee break Coffee break Coffee break

Session 2

11.00-13.00

  

Oral presentations 2

 Oral presentations 5 Oral presentations 7 Oral presentations 10

Lunch

13.00-14.30

   Lunch Lunch Lunch Lunch

Session 3

14.30-16.00

  

Oral presentations 3

Invited speaker:

Christiane Fellbaum

 FREE Oral presentations 8 END

Coffee break

16.00-16.30

   Coffee break FREE Coffee break  

Session 4

16.30-17.30

   Poster session FREE GWA business meeting  
Social event Welcome cocktail Informal hangout

Cultural activity and

conference dinner

 Informal hangout  

Programme in detail

All the conference activities will be held in the Joxe Mari Korta Centre, unless differently stated. The sessions on Thursday, Jan 26, will be held in the Carlos Santamaria Auditorium.

 

Monday, January 23

Tuesday, January 24

  • 8.30: Registration
  • 9.00-10.30: Opening and oral presentation session 1 - Chair: Kiril Simov
    • Filip Klubička and John Kelleher. Probing Taxonomic and Thematic Embeddings for Taxonomic Information. PDF and slides
    • Wondimagegnhue Tufa, Lisa Beinborn and Piek Vossen. A WordNet View on Crosslingual Transformers. PDF and slides
    • Julie Kallini and Christiane Fellbaum. What to Make of make? Sense Distinctions for Light Verbs. PDF
  • 10.30-11.00: Coffee break
  • 11.00-13.00: Oral presentation session 2 - Chair: Piek Vossen
    • Javier Álvez, Itziar Gonzalez-Dios and German Rigau. Towards Effective Correction Methods Using WordNet Meronymy Relations. PDF and slides
    • Hugo Gonçalo Oliveira. Studying the Acquisition of WordNet Relations from Pretrained Masked Language Models for Portuguese. PDF and slides
    • Konrad Wojtasik, Arkadiusz Janz and Maciej Piasecki. Wordnet for Data Augmentation in Pretraining for Encoder-Decoder Architecture. PDF and slides
    • Arkadiusz Janz and Marek Maziarz. Data Augmentation Method for Boosting Multilingual Word Sense Disambiguation. PDF and slides
  • 13.00-14.30: Lunch
  • 14.30-15.00: Oral presentation session 3 - Chair: German Rigau
    • Eric Kafe. Mapping wordnets on the fly. PDF and slides
  • 15.00-16.00: Invited talk: Christiane Fellbaum - Chair: German Rigau
  • 16.00-16.30: Coffee break
  • 16.30: Poster session and informal hangout - Chair: Alexandre Rademaker
    • Erica Biagetti, Chiara Zanchi and Silvia Luraghi. Linking the Sanskrit WordNet to the Vedic Dependency Treebank: a pilot study. PDF
    • Oğuzhan Kuyrukçu, Ezgi Sanıyar and Olcay Taner Yildiz. StarNet: A WordNet Editor Interface. PDF
    • Cécile Robin, Atharva Kulkarni and Paul Buitelaar. Identifying FrameNet Lexical Semantic Structures for Knowledge Graph Extraction from Financial Customer Interactions. PDF
    • Fahad Khan, John P. McCrae, Francisco Javier Minaya Gómez, Rafael Cruz González and Javier E. Díaz-Vera. Some Considerations in the Construction of a Historical Language WordNet. PDF
    • Ramona Kuehn, Jelena Mitrović and Michael Granitzer. Hidden in Plain Sight: Can German Wiktionary and Wordnets Facilitate the Detection of Antithesis? PDF
    • Nathalie Sørensen, Sanni Nimb and Bolette Pedersen. How do We Treat Systematic Polysemy in Wordnets and Similar Resources? – Using Human Intuition and Contextualized Embeddings as Guidance. PDF
    • Elena Irimia and Verginica Mititelu. The Romanian Wordnet in Linked Open Data Format. PDF
    • Luca Brigada Villa, Erica Biagetti, Riccardo Ginevra and Chiara Zanchi. Combining WordNets with Treebanks to study idiomatic language: A pilot study on Rigvedic formulas through the lenses of the Sanskrit WordNet and the Vedic Treebank. PDF
    • Arkadiusz Janz and Maciej Piasecki. Word Sense Disambiguation Based on Iterative Activation Spreading with Contextual Embeddings for Sense Matching. PDF
    • Francis Bond, Luis Morgado da Costa, Ewa Rudnicka, Alexandre Rademaker and Michael Wayne Goodman. Documenting the Open Multilingual Wordnet. PDF
    • Claus Zinn, Marie Hinrichs and Erhard Hinrichs. Mapping GermaNet for the Semantic Web using OntoLex-Lemon. PDF
    • Zara Kancheva. Incorporating prepositions in the BulTreeBank WordNet. PDF
    • Ineke Schuurman, Thierry Declerck, Caro Brosens, Margot Janssens, Vincent Vandeghinste and Bram Vanroy. Are there just WordNets or also SignNets? PDF

Wednesday, January 25

  • 9.00-10.00: Invited talk: José Camacho Collados - Chair: Bolette Pedersen - slides
  • 10.00-10.30: Oral presentation session 4 - Bolette Pedersen
    • Francis Bond and Takyuki Kuribayashi. The Japanese Wordnet 2.0. PDF and slides
  • 10.30-11.00: Coffee break
  • 11.00-13.00: Oral presentation session 5 - Chair: Maciej Piasecki
    • Peteris Paikens, Agute Klints, Ilze Lokmane, Lauma Pretkalniņa, Laura Rituma, Madara Stāde and Laine Strankale. Latvian WordNet. PDF and slides
    • Luis Chiruzzo, Marvin Agüero-Torales, Aldo Alvarez and Yliana Rodríguez. Initial Experiments for Building a Guarani WordNet. PDF and slides
    • Aslı Kuzgun, Oğuz Kerem Yıldız and Olcay Taner Yildiz. A CCGbank for Turkish: From Dependency to CCG. PDF and slides
    • Bolette Pedersen, Sanni Nimb, Nathalie Sørensen, Sussi Olsen, Ida Flörke and Thomas Troelsgård. Reusing the Danish WordNet for a New Central Word Register for Danish - a Project Report. PDF and slides
  • 13.00-14.30: Lunch
  • 16.30: Cultural activity - Visit to San Telmo Museum.
  • 19.30: Conference dinner at Larre Gain cider house.

Thursday, January 26 - Carlos Santamaria Auditorium (Elhuyar square, 2)

  • 9.00-10.30: Oral presentation session 6 - Chair: Francis Bond
    • Kiril Simov and Petya Osenova. Recent Developments in BTB-WordNet. PDF and slides
    • Marek Maziarz, Łukasz Grabowski, Tadeusz Piotrowski, Ewa Rudnicka and Maciej Piasecki. Lexicalised and non-lexicalized multi-word expressions in WordNet: a cross-encoder approach. PDF and slides
    • Thierry Declerck, Thomas Troelsgård and Sussi Olsen. Towards a RDF Representation of the Infrastructure consisting in using WordNet(s) as a conceptual Interlingua between multilingual Sign Language Datasets. PDF and slides
  • 10.30-11.00: Coffee break
  • 11.00-13.00: Oral presentation session 7 - Chair: Petya Osenova
    • Alexandre Rademaker, Abhishek Basu and Rajkiran Veluri. Semantic Parsing and Sense Tagging the Princeton WordNet Gloss Corpus. PDF and slides
    • Sanad Malaysha, Mustafa Jarrar and Mohammed Khalilia. Context-Gloss Augmentation for Improving Arabic Target Sense Verification. PDF and slides
    • Joanna Sio and Luis Morgado Da Costa. The Open Cantonese Sense-Tagged Corpus. PDF and slides
    • Arnob Mallik and Grzegorz Kondrak. Correcting Sense Annotations Using Wordnets and Translations. PDF and slides
  • 13.00-14.30: Lunch
  • 14.30-16.00: Oral presentation session 8 - Chair: Laurette Pretorius
    • Sana Ghanem, Mustafa Jarrar, Radi Jarrar and Ibrahim Bounhas. A Benchmark and Scoring Algorithm for Enriching Arabic Synonyms. PDF and slides
    • Ivelina Stoyanova and Svetlozara Leseva. Expanding the Conceptual Description of Verbs in WordNet with Semantic and Syntactic Information. PDF and slides
    • Ahti Lohk, Martin Rebane and Heili Orav. An Experiment: Finding Parents for Parentless Synsets by Means of CILI. PDF and slides
  • 16.00-16.30: Coffee break
  • 16.30-17.30: Global WordNet Association business meeting
  • 17.30: Informal Hangout

Friday, January 27

  • 9.00-10.30: Oral presentation session 9 - Chair: Thierry Declerck
    • Laurette Marais and Laurette Pretorius. Extending the usage of adjectives in the Zulu AfWN. PDF and slides
    • Luis Morgado Da Costa, František Kratochvíl, George Saad, Benidiktus Delpada, Daniel Simon Lanma, Francis Bond and Natálie Wolfová. Linking SIL Semantic Domains to Wordnet and Expanding the Abui Wordnet through Rapid Words Collection Methodology. PDF and slides
    • Wiktor Walentynowicz and Maciej Piasecki. Wordnet-oriented recognition of derivational relations. PDF and slides
  • 10.30-11.00: Coffee break
  • 11.00-13.00: Oral presentation session 10 and final words
    • Oscar Sainz, Oier Lopez de Lacalle, Eneko Agirre and German Rigau. What do Language Models know about word senses? Zero-Shot WSD with Language Models and Domain Inventories. PDF and slides
    • Svetla Koeva and Dimitar Hristov. Resolving Multiple Hypernymy. PDF and slides
    • Elena Zotova, Montse Cuadros and German Rigau. Towards the integration of WordNet into ClinIDMap. PDF and slides
    • Melanie Siegel and Johann Bergh. Connecting Multilingual WordNets: Strategies for Improving ILI Classification in OdeNet. PDF and slides
  • 13.00-14.30: Lunch

Invited talks

 

 

Christiane Fellbaum

35 years of WordNet: Taking stock and looking ahead

Abstract:

We provide a brief behind-the-scenes look at the early days of WordNet, highlighting its initial motivation and its evolution. Examples of WordNet's current and potential future contributions to research in linguistics and psycholinguistics as well as to a wide range of applications are discussed.

 

Bio:

Christiane Fellbaum is a Lecturer with Rank of Professor in the Program in Linguistics and the Computer Science Department at Princeton University. She was educated in Germany, France, and the U.S. and received her Ph.D. in Linguistics from Princeton University. She is a co-developer, with George A. Miller, of the lexical database WordNet, and has been active in WordNet-related research and diverse applications. She has published widely on topics in lexical semantics and computational linguistics.

 

 

 

José Camacho-Collados

Contextualized Embeddings, Word Sense Disambiguation and Open Challenges


Abstract: 

Embeddings have been one of the most important topics of interest in Natural Language Processing (NLP) for the past decade. Representing knowledge through low-dimensional vectors that are flexible and easily integrable in modern machine learning models has played a central role in the development of the field. Embedding techniques initially focused on words but the attention soon started to shift to other forms. Recently, contextualized embeddings such as those provided by BERT and similar approaches have taken NLP by storm, providing improvements in many downstream tasks. Unlike static word embeddings, contextualized models can dynamically capture the meaning of a word in context. In this talk, I will explain to what extent this is true, showing the main advantages and limitations of current approaches. I will take word sense disambiguation as a proxy to answer these questions, presenting an overview of the field from a language modelling perspective and discussing open challenges.


Bio:
Jose Camacho-Collados is a Senior Lecturer and UKRI Future Leaders Fellow at Cardiff University, leading the Cardiff NLP group. Before joining Cardiff University, he completed his PhD in Sapienza University of Rome and was a Google AI PhD Fellow. He has worked on different areas of Natural Language Processing (NLP) with a particular focus on semantics. He is the co-author of the “Embeddings in Natural Language Processing" book and is the current Program Chair of *SEM. In addition to semantics, he is interested in lexical resources and multilinguality, and in the last few years he has worked on developing NLP models specialised in social media, such as those included in the recently released TweetNLP platform.