Persona:
Fresno Fernández, Víctor Diego

Foto de perfil
Dirección de correo electrónico
ORCID
0000-0003-4270-2628
Fecha de nacimiento
Proyectos de investigación
Unidades organizativas
Puesto de trabajo
Apellidos
Fresno Fernández
Nombre de pila
Víctor Diego
Nombre

Filtros

2022 - 20253
Restablecer filtros

Ajustes

Tipo: conference proceedings ×

Resultados de la búsqueda

Mostrando 1 - 3 de 3
  • Miniatura
    Publicación
    Is anisotropy really the cause of BERT embeddings not being semantic?
    (Association for Computational Linguistics, 2022-01-01) Fuster Baggetto, Alejandro; Fresno Fernández, Víctor Diego
    In this paper we conduct a set of experiments aimed to improve our understanding of the lack of semantic isometry in BERT, i.e. the lack of correspondence between the embedding and meaning spaces of its contextualized word representations. Our empirical results show that, contrary to popular belief, the anisotropy is not the root cause of the poor performance of these contextual models’ embeddings in semantic tasks. What does affect both the anisotropy and semantic isometry is a set of known biases: frequency, subword, punctuation, and case. For each one of them, we measure its magnitude and the effect of its removal, showing that these biases contribute but do not completely explain the phenomenon of anisotropy and lack of semantic isometry of these contextual language models.
  • Miniatura
    Publicación
    Robust Estimation of Population-Level Effects in Repeated-Measures NLP Experimental Designs
    (Association for Computational Linguistics, 2025-01-01) Benito Santos, Alejandro; Ghajari Espinosa, Adrián; Fresno Fernández, Víctor Diego
    NLP research frequently grapples with multiple sources of variability—spanning runs, datasets, annotators, and more—yet conventional analysis methods often neglect these hierarchical structures, threatening the reproducibility of findings. To address this gap, we contribute a case study illustrating how linear mixed-effects models (LMMs) can rigorously capture systematic language-dependent differences (i.e., population-level effects) in a population of monolingual and multilingual language models. In the context of a bilingual hate speech detection task, we demonstrate that LMMs can uncover significant population-level effects—even under low-resource (small-N) experimental designs—while mitigating confounds and random noise. By setting out a transparent blueprint for repeated-measures experimentation, we encourage the NLP community to embrace variability as a feature, rather than a nuisance, in order to advance more robust, reproducible, and ultimately trustworthy results.
  • Miniatura
    Publicación
    The Reader is the Metric: How Textual Features and Reader Profiles Explain Conflicting Evaluations of AI Creative Writing
    (Association for Computational Linguistics, 2025-01-01) Marco Remón, Guillermo; Gonzalo Arroyo, Julio Antonio; Fresno Fernández, Víctor Diego
    Recent studies comparing AI-generated and human-authored literary texts have produced conflicting results: some suggest AI already surpasses human quality, while others argue it still falls short. We start from the hypothesis that such divergences can be largely explained by genuine differences in how readers interpret and value literature, rather than by an intrinsic quality of the texts evaluated. Using five public datasets (1,471 stories, 101 annotators including critics, students, and lay readers), we (i) extract 17 reference-less textual features (e.g., coherence, emotional variance, average sentence length...); (ii) model individual reader preferences, deriving feature importance vectors that reflect their textual priorities; and (iii) analyze these vectors in a shared “preference space”. Reader vectors cluster into two profiles: _surface-focused readers_ (mainly non-experts), who prioritize readability and textual richness; and _holistic readers_ (mainly experts), who value thematic development, rhetorical variety, and sentiment dynamics. Our results quantitatively explain how measurements of literary quality are a function of how text features align with each reader’s preferences. These findings advocate for reader-sensitive evaluation frameworks in the field of creative text generation.