Persona: Fresno Fernández, Víctor Diego
Cargando...
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
9 resultados
Resultados de la búsqueda
Mostrando 1 - 9 de 9
Publicación Speech gestural interpretation by applying word representations in robotics(IOS Press, 2018-12-03) Almagro Cádiz, Mario; Paz López, Félix de la; Fresno Fernández, Víctor DiegoHuman-Robot Interaction (HRI) is a growing area of interest in Artificial Intelligence that aims to make interaction with robots more natural. In this sense, numerous research studies on verbal and visual interactions with robots have appeared. The present paper will focus on non-verbal communication and, more specifically, gestures related to speech, which is an open question. With the aim of developing this part of Human-Robot Interaction or HRI, a new architecture is proposed for the assignment of gestures to speech based on the analysis of semantic similarities. In this way, gestures will be intelligently selected using Natural Language Processing (NLP) techniques. The conditions for gesture selection will be determined from an assessment of the effectiveness of different language models in a lexical substitution task applied to gesture annotation. On the basis of this analysis, the aim is to compare models based on expert knowledge and statistical models generated from lexical learning.Publicación Test-driving information theory-based compositional distributional semantics: A case study on Spanish song lyrics(ELSEVIER, 2025-06-15) Ghajari Espinosa, Adrián; Benito Santos, Alejandro; Ros Muñoz, Salvador; Fresno Fernández, Víctor Diego; González Blanco, ElenaSong lyrics pose unique challenges for semantic similarity assessment due to their metaphorical language, structural patterns, and cultural nuances - characteristics that often challenge standard natural language processing (NLP) approaches. These challenges stem from a tension between compositional and distributional semantics: while lyrics follow compositional structures, their meaning depends heavily on context and interpretation. The Information Theory-based Compositional Distributional Semantics framework offers a principled approach by integrating information theory with compositional rules and distributional representations. We evaluate eight embedding models on Spanish song lyrics, including multilingual, monolingual contextual, and static embeddings. Results show that multilingual models consistently outperform monolingual alternatives, with the domain-adapted ALBERTI achieving the highest F1 macro scores (78.92 ± 10.86). Our analysis reveals that monolingual models generate highly anisotropic embedding spaces, significantly impacting performance with traditional metrics. The Information Contrast Model metric proves particularly effective, providing improvements up to 18.04 percentage points over cosine similarity. Additionally, composition functions maintaining longer accumulated vector norms consistently outperform standard averaging approaches. Our findings have important implications for NLP applications and challenge standard practices in similarity calculation, showing that effectiveness varies with both task nature and model characteristics.Publicación DISCO PAL: Diachronic Spanish sonnet corpus with psychological and affective labels(Springer, 2021-10-13) Barbado, Alberto; Fresno Fernández, Víctor Diego; Manjarrés Riesco, Ángeles; Ros Muñoz, SalvadorNowadays, there are many applications of text mining over corpora from different languages. However, most of them are based on texts in prose, lacking applications that work with poetry texts. An example of an application of text mining in poetry is the usage of features derived from their individual words in order to capture the lexical, sublexical and interlexical meaning, and infer the General Affective Meaning (GAM) of the text. However, even though this proposal has been proved as useful for poetry in some languages, there is a lack of studies for both Spanish poetry and for highly-structured poetic compositions such as sonnets. This article presents a study over an annotated corpus of Spanish sonnets, in order to analyse if it is possible to build features from their individual words for predicting their GAM. The purpose of this is to model sonnets at an affective level. The article also analyses the relationship between the GAM of the sonnets and the content itself. For this, we consider the content from a psychological perspective, dentifying with tags when a sonnet is related to a specific term. Then, we study how GAM changes according to each of those psychological terms. The corpus used contains 274 Spanish sonnets from authors of different centuries, from fifteenth to nineteenth. This corpus was annotated by different domain experts. The experts annotated the poems with affective and lexico-semantic features, as well as with domain concepts that belong to psychology. Thanks to this, the corpus of sonnets can be used in different applications, such as poetry recommender systems, per- sonality text mining studies of the authors, or the usage of poetry for therapeutic purposes.Publicación Logic replicant: a new machine learning algorithm for multiclass classification in small datasets(IOP Publishing, 2025-04-11) Corral, Pedro; Centeno Sánchez, Roberto; Fresno Fernández, Víctor DiegoMulticlass classification with small datasets often presents a significant challenge for conventional machine learning (ML) algorithms, predicting with an accuracy affected by this context of data scarcity. To remedy this, this papers presents a novel ML model based on a differentiable deterministic finite-state machine (DFSM) that improves the prediction performance compared with state-of-the-art multiclass classifiers applied in this ambit of small data per class. The proposed model uses a logic-arithmetic function that replicates the inherent classification logic of the problem rather than finding patterns of feature similarity. Our algorithm, called logic replicant, allows to learn problems that other classification models cannot. As the logic replicant is a DFSM it can learn any combinational logic, but it goes beyond this point learning other types of problems such as handwritten-digit recognition, and the detection of mice with Down syndrome based on the presence of 77 proteins. Our ML algorithm is also easy to interpret using quantitative diagrams, in comparison to less interpretable algorithms such as artificial neural networks, random forest, and others. The results obtained with different data sets related to math, physics, biology and image recognition show that our design based on a logic-arithmetic function and being a DFSM improves the generalisation capacity (better prediction accuracy) of the logic replicant compared to other state-of-the-art ML approaches.Publicación ICD-10 Coding of Spanish Electronic Discharge Summaries: An Extreme Classification Problem(Institute of Electrical and Electronics Engineers, 2020-06-08) Almagro, Mario; Martínez Unanue, Raquel; Fresno Fernández, Víctor Diego; Montalvo, SotoMedical coding is used to identify and standardize clinical concepts in the records collected from healthcare services. The tenth revision of the International Classification of Diseases (ICD-10) is the most widely-used coding with more than 11,000 different diagnoses, affecting research, reporting, and funding. Unfortunately, ICD-10 code sets tend to follow biased, unbalanced, and scattered distributions. These distribution attributes, along with high lexical variability, severely restrict performance when coded clinical records are used to infer code sets in uncoded records. To improve that inference, we explore a combination of example-based methods optimized to capture codes with different appearance frequencies in data sets. Materials and Methods: The proposed exploration has been carried out on Spanish hospital discharge reports coded by experts, excluding all sentences without any biomedical concept. Representations based on semantic and lexical features are explored, using both global and label-specific attributes. In turn, algorithms based on binary outputs, groups of subsets and extreme classification are compared. Lists of codes together with their confidence values (certainty probabilities) are suggested by each method. Results: Diverse spectral behaviors are shown for each method. Binary classifiers seem to maximize the capture of more popular codes, while extreme classifiers promote infrequent ones. In order to exploit such differences, ensemble approaches are proposed by weighting every output code according to the method, confidence value and appearance frequency. The rule-based combination reaches a 46% Precision at 10 ( P@10 ), which means a 15% improvement over the best individual proposal. Conclusion: Assembling methods based on weighting each code according to training frequency and performance can achieve better overall Precision scores on extreme distributions, such as ICD-10 coding.Publicación Information Theory–based Compositional Distributional Semantics(Massachusetts Institute of Technology Press, 2022-12-01) Amigo Cabrera, Enrique; Ariza Casabona, Alejandro; Fresno Fernández, Víctor Diego; Martí, M. AntòniaIn the context of text representation, Compositional Distributional Semantics models aim to fuse the Distributional Hypothesis and the Principle of Compositionality. Text embedding is based on co-ocurrence distributions and the representations are in turn combined by compositional functions taking into account the text structure. However, the theoretical basis of compositional functions is still an open issue. In this article we define and study the notion of Information Theory–based Compositional Distributional Semantics (ICDS): (i) We first establish formal properties for embedding, composition, and similarity functions based on Shannon’s Information Theory; (ii) we analyze the existing approaches under this prism, checking whether or not they comply with the established desirable properties; (iii) we propose two parameterizable composition and similarity functions that generalize traditional approaches while fulfilling the formal properties; and finally (iv) we perform an empirical study on several textual similarity datasets that include sentences with a high and low lexical overlap, and on the similarity between words and their description. Our theoretical analysis and empirical results show that fulfilling formal properties affects positively the accuracy of text representation models in terms of correspondence (isometry) between the embedding and meaning spaces.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 DiegoRecent 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.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 DiegoNLP 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.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 DiegoIn 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.