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

BMC Bioinformatics,

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)

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

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.

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, 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

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

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.

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

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

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.

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

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

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

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

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

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

eHizpide 101

NeuroImage

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

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

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