publications

Sara Gracia, Maite Oronoz, Alicia Pérez

Ideiagintza suizidaren identifikazioa sare sozialetan (2023)

IKERGAZTE NAZIOARTEKO IKERKETA EUSKARAZ. UEU. 2023ko maiatzaren 17,18 eta 19. Donostia

Iakes Goenaga, Edgar Andrés, Koldo Gojenola, Aitziber Atutxa

Advances in Monolingual and Crosslingual Automatic Disability Annotation in Spanish (2023)

BMC Bioinformatics,

Alicia Pérez, Maite Oronoz, Juan Martinez-Romo, Lourdes Araujo

OBSER-MENH: Digital OBSERvatory of MENtal Health in social networks for Healthcare Institutions based on Language Technologies (2023)

Accepted (not published). Proceedings of the Annual Conference of the Spanish Association for Natural Language Processing: Projects and Demonstrations (SEPLN-PD 2023) co-located with the Conference of the Spanish Society for Natural Language Processing (SEPLN 2023)

Izaskun Aldezabal, María Jesús Aranzabe

Euskararen eredutik hizkuntza-ereduen euskarara (2023)

David Lindemann (arg.), Miren Azkarateri esker onez, 57-75. Bilbo: UPV/EHUko Argitalpen Zerbitzua

Masson, M., Roose, P., Sallaberry, C., Agerri, R., Bessagnet, MN., Lacayrelle, A.L.P

APs: A Proxemic Framework for Social Media Interactions Modeling and Analysis (2023)

In: Crémilleux, B., Hess, S., Nijssen, S. (eds) Advances in Intelligent Data Analysis XXI. IDA 2023. Lecture Notes in Computer Science, vol 13876. Springer, Cham.

Gorka Urbizu, Iñaki San Vicente, Xabier Saralegi, Rodrigo Agerri, Aitor Soroa

Scaling Laws for BERT in Low-Resource Settings (2023)

Findings of the Association for Computational Linguistics: ACL 2023

Nayla Escribano, German Rigau, Rodrigo Agerri

A modular approach for multilingual timex detection and normalization using deep learning and grammar-based methods (2023)

Nayla Escribano, German Rigau, Rodrigo Agerri, A modular approach for multilingual timex detection and normalization using deep learning and grammar-based methods, Knowledge-Based Systems, Volume 273, 2023, 110612, ISSN 0950-7051, https://doi.org/10.1016/j.knosys.2023.110612. (https://www.sciencedirect.com/science/article/pii/S0950705123003623) Abstract: Detecting and normalizing temporal expressions is an essential step for many NLP tasks. While a variety of methods have been proposed for detection, best normalization approaches rely on hand-crafted rules. Furthermore, most of them have been designed only for English. In this paper we present a modular multilingual temporal processing system combining a fine-tuned Masked Language Model for detection, and a grammar-based normalizer. We experiment in Spanish and English and compare with HeidelTime, the state-of-the-art in multilingual temporal processing. We obtain best results in gold timex normalization, timex detection and type recognition, and competitive performance in the combined TempEval-3 relaxed value metric. A detailed error analysis shows that detecting only those timexes for which it is feasible to provide a normalization is highly beneficial in this last metric. This raises the question of which is the best strategy for timex processing, namely, leaving undetected those timexes for which is not easy to provide normalization rules or aiming for high coverage. Keywords: Temporal processing; Multilingualism; Sequence labeling; Grammar-based approaches; Deep learning; Natural language processing

Rodrigo Agerri, Eneko Aigrre

Lessons learned from the evaluation of Spanish Language Models (2023)

Procesamiento del Lenguaje Natural (70), pp 157-170

Kepa Sarasola, Itziar Aldabe, Nora Aranberri

Enabling additional official languages in the EU for 2025 with language-centred Artificial Intelligence (2023)

Special issue of 'De Europa' journal "Llinguistic rights, multilingualism and language varieties in Europe in the age of artificial intelligence" pp.93-107. Turin, 2023.

Itziar Aduriz, Manex Agirrezabal, Eneko Agirre, Iñaki Alegria, Xabier Arregi, Jose Mari Arriola Xabier Artola, Arantza Díaz de Ilarraza, Ainara Estarrona, Izaskun Etxeberria, Nerea Ezeiza, Kepa Sarazola

Mofologia Konputazionala Euskaraz, 35 urte (2023)

Lindemann, D. (arg.). Miren Azkarateri esker onez, 15-30. UPV/EHU Argitalpen zerbitzua. Bilbo.

David Lindemann, Aitzol Astigarraga, Marije Bidaguren, Emilio Delgado, Galder Gonzalez, Kepa Sarasola

Inguma eta Wikidata uztartuz, euskarazko zientziaren ezagutza-graforantz (2023)

Lindemann, D. (arg.). Miren Azkarateri esker onez, 15-30. UPV/EHU Argitalpen zerbitzua. Bilbo.

Murali Kondragunta, Olatz Perez-de-Viñaspre, Maite Oronoz

Improving and Simplifying Template-Based Named Entity Recognition (2023)

In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop, pages 79–86, Dubrovnik, Croatia. Association for Computational Linguistics. May 2023, Dubrovnik, Croatia.

Aner Egaña, Itziar Aldabe, Oier Lopez de Lacalle

Exploration of Annotation Strategies for Automatic Short Answer Grading (2023)

The 24th International Conference on Artificial Intelligence in Education, AIED 2023

Igone Zabala

Euskararen erregistro akademikoen garapenaz: hiztegia eta fraseologia (2023)

Lindemann David (ed.) Miren Azkarateri esker onez. Bilbo: UPV/EHUko Argitalpen Zerbitzua: 313-332

Miriam Peña-Zabala, Nagore Martinez-Merino, Mikel Iruskieta

UBE: Hezkuntza komunitatea elkareraginean (2023)

Estructura modular, metodologías activas y compromiso social en innovación educativa universitaria: La experiencia de la Facultad de Educación de Bilbao, UPV/EHU (2011-2021)

Ainara Estarrona, Izaskun Etxeberria, Manuel Padilla-Moyano, Ander Soraluze

Measuring language distance for historical texts in Basque (2023)

Procesamiento del Lenguaje Natural, Revista no 70, marzo del 2023, pp. 53-61

Oscar Sainz, Oier Lopez de Lacalle, Eneko Agirre, German Rigau

What do Language Models know about word senses? Zero-Shot WSD with Language Models and Domain Inventories (2023)

Proceedings of the 12th Global WordNet Conference pages 44–52, University of South Africa (UNISA). Global Wordnet Association.

Paula Ontalvilla, Aitziber Atutxa, Maite Oronoz

Osasun-arloko entitate izendunen etiketatzea (2023)

IkerGazte 2023- Ikertzaile Euskaldunen Bosgarren kongresua (https://ikergazte.ueu.eus/)

Ekain Arrieta, Igor Odriozola, Xabier Arregi, Mikel Iruskieta

HABE-IXA euskarazko idazmen-proben corpuseko idazlanen mailakatze automatikoa (2023)

eHizpide 101

Anastasia Klimovich-Gray, Giovanni Di Liberto, Lucia Amoruso, Ander Barrena, Eneko Agirre, Nicola Molinaro

Increased top-down semantic processing in natural speech linked to better reading in dyslexia (2023)

NeuroImage

Celia Soler Uguet, Nora Aranberri

Exploring politeness control in NMT: fine-tuned vs. multi-register models in Castilian Spanish (2023)

Revista Procesamiento del Lenguaje Natural, 70, pp. 199-212.

Irune Ibarra, Mikel Iruskieta

Intervención individualizada de la transcripción escrita con smartpen y basada en corpus lingüísticos: casos de 2 niños mellizos con trastorno del desarrollo del lenguaje (TDL) (2023)

GRAO 62: Análisis y estudios. 38-49 or.

Ander Salaberria, Gorka Azkune, Oier Lopez de Lacalle, Aitor Soroa, Eneko Agirre

Image captioning for effective use of language models in knowledge-based visual question answering (2023)

Expert Systems with Applications, 2023, vol. 212, p. 118669. Preprint: https://arxiv.org/abs/2109.08029