Publications (114) Aitor Soroa Etxabe publications

2024

  1. DeepKnowledge: Deep Multilingual Language Model Technology for Language Understanding

    CEUR Workshop Proceedings

  2. DeepR3: Reducing, Reusing and Recycling Large Models for Developing Responsible and Green Language Technologies

    CEUR Workshop Proceedings

  3. Do Multilingual Language Models Think Better in English?

    Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024

  4. ENIA Chair in Artificial Intelligence and Language Technology

    CEUR Workshop Proceedings

  5. IKER-GAITU: Research on Language Technology for Basque and Other Low-Resource Languages

    CEUR Workshop Proceedings

  6. Ixa at RefutES 2024: Leveraging Language Models for Counter Narrative Generation

    CEUR Workshop Proceedings

  7. Latxa: An Open Language Model and Evaluation Suite for Basque

    Proceedings of the Annual Meeting of the Association for Computational Linguistics

  8. XNLIeu: a dataset for cross-lingual NLI in Basque

    Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024

2023

  1. Deep Dive Text Analytics and Natural Language Understanding

    Cognitive Technologies (Springer Science and Business Media Deutschland GmbH), pp. 313-336

  2. Image captioning for effective use of language models in knowledge-based visual question answering

    Expert Systems with Applications, Vol. 212

  3. Scaling Laws for BERT in Low-Resource Settings

    Proceedings of the Annual Meeting of the Association for Computational Linguistics

  4. State-of-the-Art in Language Technology and Language-centric Artificial Intelligence

    Cognitive Technologies (Springer Science and Business Media Deutschland GmbH), pp. 13-38

2022

  1. BasqueGLUE: A Natural Language Understanding Benchmark for Basque

    2022 Language Resources and Evaluation Conference, LREC 2022

  2. Does Corpus Quality Really Matter for Low-Resource Languages?

    Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

  3. KIDE4Assistant: an Ontology-Driven Dialogue System Adaptation for Assistance in Maintenance Procedures

    CEUR Workshop Proceedings

  4. KIDE4I: A Generic Semantics-Based Task-Oriented Dialogue System for Human-Machine Interaction in Industry 5.0

    Applied Sciences (Switzerland), Vol. 12, Núm. 3

  5. PoeLM: A Meter- and Rhyme-Controllable Language Model for Unsupervised Poetry Generation

    Findings of the Association for Computational Linguistics: EMNLP 2022, December 7-11, 2022

  6. PoeLM: A Meter- and Rhyme-Controllable Language Model for Unsupervised Poetry Generation

    Findings of the Association for Computational Linguistics: EMNLP 2022

  7. Principled Paraphrase Generation with Parallel Corpora

    Proceedings of the Annual Meeting of the Association for Computational Linguistics

  8. The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset

    Advances in Neural Information Processing Systems