* Back to the UniDive 2nd general meeting page

As a response to the call for abstracts, we received 52 abstracts with the following breakdown: WG1 - 19, WG2 - 2, WG3 - 14, WG4 - 7. They were reviewed and selected following the double-blind standards. We selected 40 abstracts, the acceptance rate was 77%. The selected abstracts will be presented on Thursday (8 Feb 2024):

• in plenary booster sessions (1 minute per poster)
• in classical poster sessions

In the following lists, the presenters' names are underlined.

Instructions for abstract presenters have been published.

1. Challenges for corpus annotation of copulative perception verbs - Alon Fishman (abstract, poster, slide)
2. Annotating French MWEs for French L2 learning - Amalia Todirascu (abstract, poster, slide)
3. Features of Annotation of Verb Complements in Different Stages and Varieties of Armenian - Anna Danielyan (abstract, poster, slide)
4. Abstractive text summarization datasets, models, and tokenization approaches for Turkish and Hungarian - Batuhan Baykara, Tunga Gungor (abstract, poster, slide)
5. Bridging the Geological Lexicon and Corpus with Focus on MWEs Extraction - Biljana Rujević, Cvetana Krstev, Mihailo Škorić (abstract, poster, slide)
6. A taxonomy proposal for multiword expressions - Carlos Ramisch (abstract, poster, slide)
7. UD syntax for the ELEXIS parallel sense-annotated corpus: a pilot study - Carole Tiberius, Jaka Čibej, Jelena Kallas, Kadri Muischnek, Simon Krek(abstract, poster, slide)
8. Leveraging Linked Data, NIF, and CONLL-U for Enhanced Annotation in Sentence Aligned Parallel Corpora - Ranka Stanković, Christian Chiarcos, Milica Ikonić Nešić (abstract, poster, slide)
9. Idiom Corpora Construction via Large Language Models - Doğukan Arslan, Gülşen Eryiğit (abstract, poster, slide)
10. Advances in Natural Language Processing: Bridging Text and Knowledge via Grounding and Innovative Applications - Edoardo Barba, Riccardo Orlando, Pere-Lluís Huguet Cabot, Roberto Navigli (abstract, poster, slide)
11. Analyzing adjectival homonyms and polysemy: Unsupervised methods for enhanced Large Language Model understanding - Enikő Héja, Noémi Ligeti-Nagy (abstract, poster, slide)
12. Probing Coreference Models of Romance Languages using Multiword Expressions - Evelin Amorim (abstract, poster, slide)
13. Multilingual semi-automated identification and annotation of multiword expressions - Ilan Kernerman (abstract, poster, slide)
14. Verbal multiword expressions in the Croatian verb valency database - Ivana Brač, Lobel Filipić, Maja Matijević, Siniša Runjaić (abstract, poster, slide)
15. ArboratorGrew: Collaborative Curation for Treebank Manipulation - Khensa Daoudi, Kim Gerdes, Gaël Guibon, Bruno Guillaume, Kirian Guiller (abstract, poster, slide)
16. Word Segmentation in Universal Dependencies - Kilian Evang, Daniel Zeman (abstract, poster, slide)
17. Entropy Behaviour upon Dataset Size Update - Louis Estève, Agata Savary, Thomas Lavergne (abstract, poster, slide)
18. Variability Across Languages in Zero-Shot Multilingual Learning - Manon Scholivet (abstract, poster, slide)
19. Language Identification Problem of Ukrainian Corpora / Creation Dataset of Token Language Identification for Ukrainian-Russian Code-switching Corpus - Olha Kanishcheva, Maria Shvedova (abstract, poster, slide)
20. On the Inter-Linguistic Disparity of Knowledge Graphs: Bridging the Gap between English and Non-English Languages - Simone Conia (abstract, poster, slide)

1. Unifying the Annotations in Turkic Universal Dependencies Treebanks - Cagri Coltekin, Furkan Akkurt, Olcay Taner Yildiz, Sardana Ivanova, Tunga Gungor, Suzan Uskudarli, Mehmet Oguz Derin, Aida Kasieva, Gulnura Dzhumalieva, Bermet Chontaeva, Jonathan Washington, Soudabeh Eslami, Chihiro Taguchi, Aslı Kuzgun, Büşra Marşan (abstract, poster, slide)
2. Annotation of MWEs and NEs in the Serbian extension of ELEXIS-WSD: comparisons, solutions and open questions - Cvetana Krstev, Aleksandra Markovic, Ranka Stanković (abstract, poster, slide)
3. Towards a Dutch Parseme Corpus - Gosse Bouma, Jan Odijk, Carole Tiberius (abstract, poster, slide)
4. English-Bulgarian Comparable Corpus Annotated with FrameNet Valence Patterns - Ivelina Stoyanova (abstract, poster, slide)
5. A Constructicon for Universal Dependencies - Joakim Nivre (abstract, poster, slide)
6. Universal Dependencies Treebank for Standard Albanian - Nelda Kote, Anila Cepani, Alba Haveriku (abstract, poster, slide)
7. Creativity, productivity and diversity: The case of Hebrew possessive constructions - Nurit Melnik, Ittamar Erb (abstract, poster, slide)
8. Revitalizing the historical Romanian texts with Cyrillic Scripts - Olesea Caftanatov, Ludmila Malahov, Tudor Bumbu (abstract, poster slide)
9. “The ”“tongueprint”“ as language identification tool: Elaborating the proof-of-concept” - Raf Van Rooy, Flavio Massimiliano Cecchini, Isabelle Maes (abstract, poster, slide)
10. Enhancing Interoperability for Under-Resourced Language Datasets: A Case Study on Linking Lithuanian-English Cybersecurity Data - Christian Chiarcos, Maxim Ionov, Andrius Utka, Sigita Rackeviciene (abstract, poster, slide)
11. Old Egyptian Multiword Expressions consisting of a head word + ib “heart” - Roberto A. Diaz Hernandez (abstract, poster, slide)
12. An Empirical Study of Multilingual Representations from Language Modeling and Translation - Shaoxiong Ji, Timothee Mickus, Vincent Segonne, Alessandro Raganato, Jörg Tiedemann (abstract, poster, slide)
13. Creating a Multilingual Wide-Coverage Multi-Layered Semantically Annotated Corpus - Simone Conia, Edoardo Barba, Abelardo Carlos Martinez Lorenzo, Pere-Lluís Huguet Cabot, Riccardo Orlando, Luigi Procopio, Roberto Navigli (abstract, poster, slide)
14. Treatment of Multiword Expressions with a view to Morphologically Rich Languages - Svetlozara Leseva (abstract, poster, slide)
15. The first Haitian Creole treebank - Sylvain Kahane, Agata Savary, Claudel Pierre-Louis (abstract,poster,slide)
16. MultiNCI - A Multilingual Noun Compound Idiomaticity Dataset - Thomas Pickard, Aline Villavicencio, B. Madalina Zgreabăn (abstract, poster, slide)
17. Morpheme-level Coreference Annotations for Pro-dropped Languages - Tuğba Pamay Arslan, Gülşen Eryiğit (abstract, poster, slide)
18. Adding Semantics to UD Markers - Tudor Voicu, Verginica Mititelu (abstract, poster, slide )
19. The Philotis Platform: Empowering Low-Resource Languages Processing - Vivian Stamou, Vasileios Arampatzakis, Dimitrios Karamatskos, Vasileios Sevetlidis, Nicolaos Valeontis, Stella Markantonatou, George Pavlidis (abstract, poster, slide)
20. Après Toi: Scoring Systems based on Dataset Votes - Yuval Pinter (abstract, poster, slide)