Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 17
Encontrada(s) 1 página(s)

RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Revisiting Supertagging for faster HPSG parsing

  • Zamaraeva, Olga
  • Gómez-Rodríguez, Carlos
Presented at: Conference on Empirical Methods in Natural Language Processing, Miami, Florida, USA,12-16 Nov. 2024., [Abstract]: We present new supertaggers trained on English HPSG-based treebanks and test the effects of the best tagger on parsing speed and accuracy. HPSG treebanks are produced automatically by large manually built grammars and feature high-quality annotation based on a well-developed linguistic theory. The English Resource Grammar treebanks include diverse and challenging test datasets, beyond the usual WSJ section 23 and Wikipedia data. HPSG supertagging has previously relied on MaxEnt-based models. We use SVM and neural CRF- and BERT-based methods and show that both SVM and neural supertaggers achieve considerably higher accuracy compared to the baseline and lead to an increase not only in the parsing speed but also the parser accuracy with respect to gold dependency structures. Our fine-tuned BERT-based tagger achieves 97.26% accuracy on 950 sentences from WSJ23 and 93.88% on the out-of-domain technical essay The Cathedral and the Bazaar. We present experiments with integrating the best supertagger into an HPSG parser and observe a speedup of a factor of 3 with respect to the system which uses no tagging at all, as well as large recall gains and an overall precision gain. We also compare our system to an existing integrated tagger and show that although the well-integrated tagger remains the fastest, our experimental system can be more accurate. Finally, we hope that the diverse and difficult datasets we used for evaluation will gain more popularity in the field: we show that results can differ depending on the dataset, even if it is an in-domain one. We contribute the complete datasets reformatted for Huggingface token classification., We acknowledge the European Union’s Horizon Europe Framework Programme which funded this research under the Marie Skłodowska-Curie postdoctoral fellowship grant HORIZON-MSCA-2021-PF-01 (GAUSS, grant agreement No 101063104); and the European Research Council (ERC), which has funded this research under the Horizon Europe research and innovation programme (SALSA, grant agreement No 101100615). We also acknowledge grants SCANNER-UDC (PID2020-113230RB-C21) funded by MICIU/AEI/10.13039/501100011033; GAP (PID2022-139308OA-I00) funded by MICIU/AEI/10.13039/501100011033/ and ERDF, EU; LATCHING (PID2023-147129OB-C21) funded by MICIU/AEI/10.13039/501100011033 and ERDF, EU; and TSI-100925-2023-1 funded by Ministry for Digital Transformation and Civil Service and “NextGenerationEU” PRTR; as well as funding by Xunta de Galicia (ED431C 2024/02), and Centro de Investigación de Galicia “CITIC”, funded by the Xunta de Galicia through the collaboration agreement between the Consellería de Cultura, Educación, Formación Profesional e Universidades and the Galician universities for the reinforcement of the research centres of the Galician University System (CIGUS)., Xunta de Galicia; ED431C 2024/02
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Unified framework for implementing inaccurate knowledge in quantum symbolic artificial intelligence models

  • Mosqueira-Rey, Eduardo
  • Magaz-Romero, Samuel
  • Moret-Bonillo, Vicente
Trabajo presentado a: 17th International Conference on Agents and Artificial Intelligence, Porto, Portugal, 23-25 February 2025., [Abstract]; Symbolic models of Artificial Intelligence are based on defining declarative knowledge that is connected through procedural knowledge forming symbolic graphs through which reasoning flows. Both declarative and procedural knowledge can be inaccurate, which has led to the definition of different models to represent this inaccuracy. Since the functioning of quantum computers is inherently probabilistic, it has been proposed to take advantage of this nature to implement inaccurate knowledge more effectively. In this paper, we present different models for implementing inaccurate knowledge in quantum computers and propose a unified framework to represent and implement the common features of all of them., This work has been supported by the EU’s Horizon 2020 under project NEASQC (grant No 951821), the State Research Agency of the Spanish Government (Grant PID2023-147422OB-I00) and by the Xunta de Galicia (Grant ED431C 2022/44), supported by the EU European Regional Development Fund (ERDF). CITIC, as a center accredited for excellence within the Galician University System and a member of the CIGUS Network, receives subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia. Additionally, it is co-financed by the EU through the FEDER Galicia 2021-27 operational program (Ref. ED431G 2023/01). We thank the support from Ministry for Digital Transformation and Civil Service and Next-GenerationEU/RRF (TSI-100925-2023-1). SMR has received funding from Xunta de Galicia (grant ED481A 2023/008)., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G 2023/01, Xunta de Galicia; ED481A 2023/008
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Sustainable Techniques to Improve Data Quality for Training Image-Based Explanatory Models for Recommender Systems

  • Paz Ruza, Jorge
  • Esteban Martínez, David
  • Alonso-Betanzos, Amparo
  • Guijarro-Berdiñas, Bertha
[Abstract]: Visual explanations based on user-uploaded images are an effective and self-contained approach to provide transparency to Recommender Systems (RS), but intrinsic limitations of data used in this explainability paradigm cause existing approaches to use bad quality training data that is highly sparse and suffers from labelling noise. Popular training enrichment approaches like model enlargement or massive data gathering are expensive and environmentally unsustainable, thus we seek to provide better visual explanations to RS aligning with the principles of Responsible AI. In this work, we research the intersection of effective and sustainable training enrichment strategies for visual-based RS explainability models by developing three novel strategies that focus on training Data Quality: 1) selection of reliable negative training examples using Positive-unlabelled Learning, 2) transform-based data augmentation, and 3) text-to-image generative-based data augmentation. The integration of these strategies in three state-of-the-art explainability models increases (5%) the performance in relevant ranking metrics of these visual-based RS explainability models without penalizing their practical long-term sustainability, as tested in multiple real-world restaurant recommendation explanation datasets, This work is funded by MICIU/AEI and ESF+ (FPU21/05783), ERDF A way of making Europe (PID2019-109238GB-C22, PID2023-147404OB-I00), ERDF/EU (PID2021-128045OA-I00), Ministry for Digital Transformation and Civil Service and ‘Next-GenerationEU’/PRTR (TSI-100925-2023-1), and Xunta de Galicia (ED431C 2022/44). CITIC is funded by “Consellería de Cultura, Educación e Universidade” through ERDF and “Secretaría Xeral de Universidades" (ED431G 2023/01)., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Hierarchical Bracketing Encodings for Dependency Parsing as Tagging

  • Ezquerro, Ana
  • Vilares, David
  • Yli-Jyrä, Anssi
  • Gómez-Rodríguez, Carlos
Presented at the 63rd Annual Meeting of the Association for Computational Linguistics, July 2025, Vienna, Austria., [Abstract]: We present a family of encodings for sequence labeling dependency parsing, based on the concept of hierarchical bracketing. We show that the existing 4-bit projective encoding belongs to this family, but it is suboptimal in the number of labels used to encode a tree. We derive an optimal hierarchical bracketing, which minimizes the number of symbols used and encodes projective trees using only 12 distinct labels (vs. 16 for the 4-bit encoding). We also extend optimal hierarchical bracketing to support arbitrary non-projectivity in a more compact way than previous encodings. Our new encodings yield competitive accuracy on a diverse set of treebanks., We acknowledge grants SCANNER-UDC (PID2020-113230RB-C21) funded by MICIU/AEI/10.13039/501100011033; GAP (PID2022-139308OA-I00) funded by MICIU/AEI/10.13039/501100011033/ and ERDF, EU; LATCHING (PID2023-147129OB-C21) funded by MICIU/AEI/10.13039/501100011033 and ERDF, EU; and TSI-100925-2023-1 funded by Ministry for Digital Transformation and Civil Service and “NextGenerationEU” PRTR; as well as funding by Xunta de Galicia (ED431C 2024/02), and CITIC, as a center accredited for excellence within the Galician University System and a member of the CIGUS Network, receives subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia. Additionally, it is co-financed by the EU through the FEDER Galicia 2021-27 operational program (Ref. ED431G 2023/01). We also extend our gratitude to CESGA, the supercomputing center of Galicia, for granting us access to its resources. Furthermore, we acknowledge the Faculty of Agriculture and Forestry of the University of Helsinki, as well as projects "Theory of Computational Logics" (352420) and "XAILOG" (345612, 345633) funded by the Research Council of Finland for the continued support of the third author during the multistage writing process., Xunta de Galicia; ED431C 2024/02, Xunta de Galicia; ED431G 2023/01, Finland. Research Council of Finland; 352420, Finland. Research Council of Finland; 345612, Finland. Research Council of Finland; 345633
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Bringing Emerging Architectures to Sequence Labeling in NLP

  • Ezquerro, Ana
  • Gómez-Rodríguez, Carlos
  • Vilares, David
Presented at: 19th Conference of the European Chapter of the Association for Computational Linguistics, March 24–29, 2026, Rabat, Morocco, [Abstract]: Pretrained Transformer encoders are the dominant approach to sequence labeling. While some alternative architectures-such as xLSTMs, structured state-space models, diffusion models, and adversarial learning-have shown promise in language modeling, few have been applied to sequence labeling, and mostly on flat or simplified tasks. We study how these architectures adapt across tagging tasks that vary in structural complexity, label space, and token dependencies, with evaluation spanning multiple languages. We find that the strong performance previously observed in simpler settings does not always generalize well across languages or datasets, nor does it extend to more complex structured tasks., We acknowledge grants GAP (PID2022-139308OA-I00) funded by MICIU/AEI/10.13039/501100011033/ and ERDF, EU; LATCHING (PID2023-147129OB-C21) funded by MICIU/AEI/10.13039/501100011033 and ERDF, EU; and TSI-100925-2023-1 funded by Ministry for Digital Transformation and Civil Service and “NextGenerationEU” PRTR; as well as funding by Xunta de Galicia (ED431C 2024/02), and CITIC, as a center accredited for excellence within the Galician University System and a member of the CIGUS Network, receives subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia. Additionally, it is co-financed by the EU through the FEDER Galicia 2021-27 operational program (Ref. ED431G 2023/01). This research project was made possible through the access granted by the Galician Supercomputing Center (CESGA) to its supercomputing infrastructure. The supercomputer FinisTerrae III and its permanent data storage system have been funded by the NextGeneration EU 2021 Recovery, Transformation and Resilience Plan, ICT2021-006904, and also from the Pluriregional Operational Programme of Spain 2014-2020 of the European Regional Development Fund (ERDF), ICTS-2019-02-CESGA-3, and from the State Programme for the Promotion of Scientific and Technical Research of Excellence of the State Plan for Scientific and Technical Research and Innovation 2013-2016 State subprogramme for scientific and technical infrastructures and equipment of ERDF, CESG15-DE-3114., Xunta de Galicia; ED431C 2024/02, Xunta de Galicia; ED431G 2023/01, Xunta de Galicia; ICTS-2019-02-CESGA-3, Xunta de Galicia; CESG15-DE-3114
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Desarrollo de competencias y responsabilidad social con IA verde

  • Morán-Fernández, Laura
  • Bolón-Canedo, Verónica
  • Dapena, Adriana
Presentado en: JENUI 2026, Actas de las XXXI Jornadas sobre la Enseñanza Universitaria de la Informática, 8 - 10 julio de 2026, Barcelona. https://jenui2026.fib.upc.edu/programa-jenui-2026/, [Resumen]: La inteligencia artificial verde (IA verde) surge como una solución orientada a mitigar el impacto ambiental de los sistemas de IA, al tiempo que introduce nuevos retos en la formación y sensibilización. En este trabajo se presentan experiencias realizadas en el año 2025 para la introducción de la IA verde en diversos contextos formativos. En primer lugar, se proponen microcredenciales como experiencias de aprendizaje activo, orientadas al desarrollo de competencias técnicas y transversales, dirigidas tanto a estudiantado universitario como a profesionales interesados en la actualización de sus conocimientos. En segundo lugar, se describe un proyecto de ciencia ciudadana con objetivos académicos y de responsabilidad social. Por último, se presentan actividades did´ acticas desarrolladas en contextos no acad´ emicos, como ferias científicas, orientadas a la divulgación y a la sensibilización sobre el impacto ambiental de la IA verde., [Abstract]: Green artificial intelligence (green AI) emerges as a solution aimed at mitigating the environmental impact of AI systems, while at the same time introducing new challenges in education and awareness-raising. This paper presents experiences carried out in 2025 for the introduction of green AI in diverse learning contexts. First, micro-credentials are proposed as active learning experiences focused on the development of technical and transversal competencies, targeting both university students and professionals interested in updating their knowledge. Second, a citizen science project with academic and social responsibility objectives is described. Finally, the paper presents educational activities developed in non-academic contexts, such as science fairs, aimed at dissemination and raising awareness of the environmental impact of AI., Este trabajo ha sido financiado parcialmente por la Cátedra UDC-Inditex de IA en Algoritmos Verdes del Ministerio para la Transformación Digital y de la Función Pública, y por “NextGenerationEU”/PRTR bajo el proyecto TSI-1009252023-1, así como por la Xunta de Galicia, con referencia ED431C 2024/18., Xunta de Galicia; ED431C 2024/18
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Autonomous Generation of Sub-goals for Lifelong Learning in Robots

  • Fallas Hernández, Emanuel
  • Martínez-Alonso, Sergio
  • Romero, Alejandro
  • Becerra Permuy, José Antonio
  • Duro, Richard J.
The conference was held in Rome, Italy, from 30 June to 5 July 2025., [Abstract]: One of the challenges of open-ended learning in robots is the need to autonomously discover goals and learn skills to achieve them. However, when in lifelong learning settings, it is always desirable to generate sub-goals with their associated skills, without relying on explicit reward, as steppingstones to a goal. This allows sub-goals and skills to be reused to facilitate achieving other goals. This work proposes a two-pronged approach for sub-goal generation to address this challenge: a top-down approach, where sub-goals are hierarchically derived from general goals using intrinsic motivations to discover them, and a bottom-up approach, where sub-goal chains emerge from making latent relationships between goals and perceptual classes that were previously learned in different domains explicit. These methods help the robot to autonomously generate and chain sub-goals as a way to achieve more general goals. Additionally, they create more abstract representations of goals, helping to reduce sub-goal duplication and make the learning of skills more efficient. Implemented within an existing cognitive architecture for lifelong open-ended learning and tested with a real robot, our approach enhances the robot’s ability to discover and achieve goals, generate sub-goals in an efficient manner, generalize learned skills, and operate in dynamic and unknown environments without explicit intermediate rewards., This work was funded by the European Union’s Horizon 2020, research and innovation programme under GA 101070381 (PILLAR-Robots - Purposeful Intrinsically-motivated Lifelong Learning Autonomous Robots’), by Xunta de Galicia (EDC431C-2021/39), by the Spanish Science and Education Ministry (PID2021-126220OB-I00), and the Ministry for Digital Transformation and Civil Service and Next-Generation EU/RRF (TSI-100925-2023-1), by “ERDF A way of making Europe”, and Centro de Investigacion de Galicia “CITIC” (ED431G 2019/01)., Xunta de Galicia; EDC431C-2021/39, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Better Benchmarking LLMs for Zero-Shot Dependency Parsing

  • Ezquerro, Ana
  • Gómez-Rodríguez, Carlos
  • Vilares, David
Presented at: Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025), pages 121–135, March 3-4, 2025 ©2025 University of Tartu Library, Código asociado: https://github.com/anaezquerro/naipar, [Abstract]: While LLMs excel in zero-shot tasks, their performance in linguistic challenges like syntactic parsing has been less scrutinized. This paper studies state-of-the-art openweight LLMs on the task by comparing them to baselines that do not have access to the input sentence, including baselines that have not been used in this context such as random projective trees or optimal linear arrangements. The results show that most of the tested LLMs cannot outperform the best uninformed baselines, with only the newest and largest versions of LLaMA doing so for most languages, and still achieving rather low performance. Thus, accurate zero-shot syntactic parsing is not forthcoming with open LLMs., We acknowledge grants SCANNER-UDC (PID2020-113230RB-C21) funded by MICIU/AEI/10.13039/501100011033; GAP (PID2022-139308OA-I00) funded by MICIU/AEI/10.13039/501100011033/ and ERDF, EU; LATCHING (PID2023-147129OB-C21) funded by MICIU/AEI/10.13039/501100011033 and ERDF, EU; and TSI-100925-2023-1 funded by Ministry for Digital Transformation and Civil Service and “NextGenerationEU” PRTR; as well as funding by Xunta de Galicia (ED431C 2024/02), and Centro de Investigación de Galicia “CITIC”, funded by the Xunta de Galicia through the collaboration agreement between the Consellería de Cultura, Educación, Formación Profesional e Universidades and the Galician universities for the reinforcement of the research centres of the Galician University System (CIGUS). We also extend our gratitude to CESGA, the supercomputing center of Galicia, for granting us access to its resources., Xunta de Galicia; ED431C 2024/02
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Fast and Frugal Transfer Learning via Precomputed Features and Adaptive Normalization

  • Vila-Cruz, Daniel
  • Bolón-Canedo, Verónica
  • Morán-Fernández, Laura
Presentado en: IDEAL 2025: International Conference on Intelligent Data Engineering and Automated Learning, 26th International Conference, Jaén, Spain, November 13–15, 2025 This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-032-10486-1_14, [Abstract]: Deep learning models, particularly convolutional neural networks (CNNs), have achieved state-of-the-art performance in medical image classification. However, their deployment in real-world clinical environments is often constrained by hardware limitations, energy requirements, and the time-intensive nature of model fine-tuning. In this work, we propose a lightweight and energy-aware training strategy that decouples feature extraction from classifier optimization. By precomputing features and adapting batch normalization statistics with a sample-aware thresholding mechanism, we reduce computational overhead without sacrificing accuracy. A redesigned classifier head is trained using a margin-based weighted loss, which emphasizes ambiguous cases without requiring end-to-end backpropagation. Experimental results on two widely used medical imaging datasets, Brain Cancer MRI and BreakHis, demonstrate that our pipeline significantly reduces training time and CO2 emissions while achieving competitive or superior accuracy compared to traditional fine-tuning approaches. This makes our method well-suited for resource-constrained settings or rapid prototyping environments., This work was supported by the Ministry of Science and Innovation of Spain (Grant PID2023-147404OB-I00/AEI /10.13039/501100011033) and together with “NextGenerationE”/PRTR by the Ministry for Digital Transformation and Civil Service under grant TSI-100925-2023-1 and by Xunta de Galicia (Grants ED431G 2023/01 and ED431C 2022/44)., Xunta de Galicia; ED431G 2023/01, Xunta de Galicia; ED431C 2022/44
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Information-Theoretic Unsupervised Feature Selection for High-Dimensional Spatial Data

  • Suárez-Marcote, Samuel
  • Vishwasrao, Abhijeet
  • Vinuesa, Ricardo
  • Morán-Fernández, Laura
  • Bolón-Canedo, Verónica
Presented at: 34th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2026), April 22 - 24, Bruges (Belgium). Available at: https://www.esann.org/proceedings/2026, [Abstract]: High-dimensional unlabelled datasets present significant challenges for efficient analysis, storage and interpretation. Unsupervised feature selection offers a way to retain the most informative variables while discarding redundant or uninformative ones, enabling more scalable processing. We introduce a spatially aware, unsupervised method that uses information theoretic criteria to identify informative variables while limiting redundancy, producing compact and spatially dispersed subsets of features. Our approach avoids dependence on labelled data or modelspecific wrappers, making it suitable for large unstructured datasets. Experiments on MNIST and EMNIST datasets, including high-resolution upscaled versions, show that the selected features preserve both discriminative structure and reconstruction quality better than chosen supervised and unsupervised baselines, demonstrating the effectiveness of entropy and mutual information coupling in unlabelled high-dimensional settings., This work was supported by Xunta de Galicia/FEDER (ED431C 2022/44); Ministerio de Ciencia e Innovación MICIU/AEI/10.13039/501100011033 and “Next-GenerationEU”/PRTR via Grant PID2023-147404OB-I00, Ministry for Digital Transformation and Civil Service (TSI100925-2023-1) and Programa de axudas á etapa predoutoral, Xunta de Galicia (ED481A 2023/034). CITIC, as an accredited Galician University System Research Center, is supported by ERDF Funds and by “Secretaría Xeral de Universidades” (Grant ED431G 2023/01)., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED481A 2023/034, Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Evaluating Compositional Approaches for Focus and Sentiment Analysis

  • Kellert, Olga
  • Imran, Muhammad
  • Matlis, Nicholas
  • Zaman, Mahmud Uz
  • Gómez-Rodríguez, Carlos
This version of the conference paper has been accepted for publication, after peer review. The Version of Record is available online at: https://doi.org/10.1007/978-3-031-92602-0_27. Presented at: CompCom 2025, 19-20 June London, United Kingdom. Part of the book series: Lecture Notes in Networks and Systems (LNNS,volume 1423)., [Abstract]: This paper summarizes the results of evaluating a compositional approach for Focus Analysis (FA) in Linguistics and Sentiment Analysis (SA) in Natural Language Processing (NLP). While quantitative evaluations of compositional and non-compositional approaches in SA exist in NLP, similar quantitative evaluations are very rare in FA in Linguistics that deal with linguistic expressions representing focus or emphasis such as “it was John who left". We fill this gap in research by arguing that compositional rules in SA also apply to FA because FA and SA are closely related meaning that SA is part of FA. Our compositional approach in SA exploits basic syntactic rules such as rules of modification, coordination, and negation represented in the formalism of Universal Dependencies (UDs) in English and applied to words representing sentiments from sentiment dictionaries. Some of the advantages of our compositional analysis method for SA in contrast to non-compositional analysis methods are interpretability and explainability. We test the accuracy of our compositional approach and compare it with a non-compositional approach VADER that uses simple heuristic rules to deal with negation, coordination and modification. In contrast to previous related work that evaluates compositionality in SA on long reviews, this study uses more appropriate datasets to evaluate compositionality. In addition, we generalize the results of compositional approaches in SA to compositional approaches in FA., We acknowledge the European Research Council (ERC), which has funded this research under the Horizon Europe research and innovation programme (SALSA, grant agreement No 101100615), ERDF/MICINN-AEI (SCANNER-UDC, PID2020-113230RB-C21), Xunta de Galicia (ED431C 2020/11), and Centro de Investigación de Galicia “CITIC”, funded by Xunta de Galicia and the European Union (ERDF - Galicia 2014–2020 Program), by grant ED431G 2019/01, LATCHING (PID2023-147129OB-C21) funded by MICIU/AEI/10.13039/501100011033 and ERDF, EU” and also ”TSI-100925-2023-1 funded by Ministry for Digital Transformation and Civil Service and “NextGenerationEU” PRTR., Xunta de Galicia; ED431C 2020/11, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Enhancing Transformer-Based Sentiment Analysis for the Rest-Mex 2025 Challenge: A Hybrid Strategy with Oversampling, Back-Translation, and Transformers

  • Imran, Muhammad
  • Rasheed, Tayyab
  • Gómez-Rodríguez, Carlos
Presented at: Researching on Evaluating Sentiment and Textual Instances Selection for Mexican Magical Towns (REST-MEX 2025), at IberLEF 2025: Natural Language Processing Challenges for Spanish and other Iberian Languages, September 2025, Zaragoza, Spain The code is available in the following GitHub repository. https://github.com/chimran135/Sentiment-Analysis-Rest-Mex-2025, [Abstract]: This paper presents a sentiment analysis framework for the Rest-Mex 2025 challenge, focused on Spanish-language reviews of Mexican Magical Towns. The task involves predicting sentiment polarity (1-5), classifying attraction type (Hotel, Restaurant, Attraction), and identifying the correct town from a list of 60. To address class imbalance, we propose a hybrid augmentation approach combining oversampling and back-translation using both structurally similar and dissimilar languages. Two transformer-based models roberta-base-bne and twitter-xlm-roberta-base are fine-tuned on the augmented datasets. The hybrid strategy, particularly with the multilingual model, achieved the best results, demonstrating improved performance and generalization across all subtasks. Our system achieved 4th place in the overall sentiment analysis track of the Rest-Mex 2025 shared task competing against 35 participating teams which demonstrates the robustness of our approach in sentiment classification across multiple subtasks. © 2025 Copyright for this paper by its authors., We acknowledge grants GAP (PID2022-139308OA-I00) funded by MICIU/AEI/10.13039/501100011033/ and ERDF, EU; LATCHING (PID2023-147129OB-C21) funded by MICIU/AEI/10.13039/501100011033 and ERDF, EU; and TSI-100925-2023-1 funded by Ministry for Digital Transformation and Civil Service and “NextGenerationEU” PRTR; as well as funding by Xunta de Galicia (ED431C 2024/02), and CITIC, as a center accredited for excellence within the Galician University System and a member of the CIGUS Network, receives subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia. Additionally, it is co-financed by the EU through the FEDER Galicia 2021-27 operational program (Ref. ED431G 2023/01)., Xunta de Galicia; ED431C 2024/02, Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Efficient ReliefF: A Low-Power Optimization of ReliefF for Resource-Constrained Devices

  • Suárez-Marcote, Samuel
  • Morán-Fernández, Laura
  • Bolón-Canedo, Verónica
This version of the conference paper has been accepted for publication, after peer review and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-032-04558-4_34. Presented at the 34th International Conference on Artificial Neural Networks, Kaunas, Lithuania, September 9–12, 2025., [Abstract]: The exponential growth of data in IoT environments requires the development of resource-efficient feature selection methods adapted for constrained devices. This work introduces two novel efficiency modifications for the ReliefF method. The first enhancement involves fixed-point arithmetic, which lowers computational overhead while improving energy and memory efficiency. The second improvement involves a single-linkage clustering step that reduces sample size without compromising data relevance. Evaluated on nine diverse datasets, ranging from those with high sample numbers to microarrays, proposed optimizations demonstrate robust performance. A 16-bit fixed-point representation achieves feature rankings comparable to 64-bit floating-point baselines, offering significant efficiency improvements. The clustering step drastically reduces execution times for large-sample datasets while preserving classification accuracy. Key findings show that the integer part of fixed-point representation, which determines the representable range, is more critical than precision. Furthermore, 16-bit implementations provide an optimal balance for most IoT applications, and clustering is vital for scalability in datasets with numerous samples. These innovations make ReliefF an effective solution for energy-limited IoT systems., This work was supported by Xunta de Galicia/FEDER (ED431C 2022/44); Ministerio de Ciencia e Innovación MCIN/AEI/10.13039/501100011033 and “Next-GenerationEU”/PRTR via Grants [PID2023-147404OB-I00, TED2021- 130599AI00]; Ministry for Digital Transformation and Civil Service (TSI-100925-2023-1) and Programa de axudas á etapa predoutoral, Xunta de Galicia (ED481A 2023/034). CITIC, as an accredited Galician University System Research Center, is supported by ERDF Funds and by “Secretaría Xeral de Universidades” (Grant ED431G 2023/01)., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED481A 2023/034, Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Communication and negotiation to improve Agent-Based Models

  • Rodríguez-Arias, Alejandro
  • Sánchez-Maroño, Noelia
  • Guijarro-Berdiñas, Bertha
O congreso tivo lugar en Porto (Portugal), do día 23 ao 25 de febreiro de 2025, [Abstract]: Agent-based models (ABM) play a fundamental role in studying and modeling complex real-world systems, primarily relying on reactive agents. Despite their simplicity, the interactions between agents and their environment enable the simulation of diverse systems, contributing to their widespread adoption, particularly in the social sciences. Similarly, though distinct in purpose, multi-agent systems (MAS) are designed to tackle complex, diverse, and distributed problems by leveraging communication, negotiation, and coordination capabilities. Both types of approaches have been used successfully in numerous areas; the power of ABM lies in thousands of interacting agents, while MAS usually employs a smaller number of agents with more capabilities. Including MAS agents’ capabilities in ABM agents allows the generation of more realistic simulations that aid in the study of the modeled systems. In this paper, we present a generic ABM model whose agents possess more capabilities, such as comm unication and negotiation, allowing this enhanced ABM to address more complex modeling problems. To exemplify the usefulness of this enhanced ABM, we propose to use it as a sandbox-tool to test “case-if” scenarios in a model that studies the evolution of a society’s opinion on a given subject, specifically in this example, the implantation of superblocks in the city of Vitoria-Gasteiz (Spain), This work was supported by the Horizon 2020 SMARTEES project (grant no. 7639) of the European Commission. We also acknowledge funding from the Xunta de Galicia and ERDF funds of the European Union through grants for research groups (ED431C 2018/34, ED431C 2022/44), CITIC as a Research Center of the University System of Galicia (ED431G 2023/01), and the Ministry for Digital Transformation and Civil Service under ‘Next-GenerationEU’/PRTR (grant TSI-100925-2023-1), Xunta de Galicia; ED431C 2018/34, Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Comparing LLM-generated and human-authored news text using formal syntactic theory

  • Zamaraeva, Olga
  • Flickinger, Dan
  • Bond, Francis
  • Gómez-Rodríguez, Carlos
The Congress took place in Vienna, Austria from July 27 to August 1st, 2025, [Abstract]: This study provides the first comprehensive comparison of New York Times-style text generated by six large language models against real, human-authored NYT writing. The comparison is based on a formal syntactic theory. We use Head-driven Phrase Structure Grammar (HPSG) to analyze the grammatical structure of the texts. We then investigate and illustrate the differences in the distributions of HPSG grammar types, revealing systematic distinctions between human and LLM-generated writing. These findings contribute to a deeper understanding of the syntactic behavior of LLMs as well as humans, within the NYT genre., We thank Ann Copestake and Emily M. Bender, and more generally the DELPH-IN community for the useful discussion related to the paper. We acknowledge grants SCANNER-UDC (PID2020-113230RB-C21) funded by MICIU/AEI/10.13039/501100011033; GAP (PID2022-139308OA-I00) funded by MICIU/AEI/10.13039/501100011033/ and ERDF, EU; LATCHING (PID2023-147129OB-C21) funded by MICIU/AEI/10.13039/501100011033 and ERDF, EU; and TSI-100925-2023-1 funded by Ministry for Digital Transformation and Civil Service and “NextGenerationEU” PRTR; as well as funding by Xunta de Galicia (ED431C 2024/02). CITIC, as a center accredited for excellence within the Galician University System and a member of the CIGUS Network, receives subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia. Additionally, it is co-financed by the EU through the FEDER Galicia 2021-27 operational program (Ref. ED431G 2023/01)., Xunta de Galicia; ED431C 2024/02, Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Quantitative and Qualitative Evaluation on Local Explainability Models for Anomaly Detection Algorithms

  • Esteban Martínez, David
  • Eiras-Franco, Carlos
  • Guijarro-Berdiñas, Bertha
  • Alonso-Betanzos, Amparo
Traballo presentado en: 18th International Work-Conference on Artificial Neural Networks, IWANN 2025, A Coruña, Spain, June 16–18, 2025 Part of the book series: Lecture Notes in Computer Science (LNCS,volume 16009), Included in the following conference series: International Work-Conference on Artificial Neural Networks This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-032-02728-3_48, [Abstract]: There is an increasingly urgent need to address the lack of transparency and clarity in the internal processes of AI (Artificial Intelligence) algorithms. In this paper, we explore local explainability techniques, LIME (Local Interpretable Model-agnostic Explanations) and SHAP (SHapley Additive exPlanations), to create a new layer of explanations on top of any anomaly detection model. This layer helps human supervisors better understand model behavior and the rationale behind its classification decisions. To assess the quality of these explanations, we conducted a qualitative analysis through a survey and a quantitative analysis using Quantus, a robust Python toolkit for evaluating explainability. The results of our experiments underscore the subtle trade-offs among various explainability techniques and emphasize the importance of carefully considering the context when applying explainability techniques., This research work is part of project PID2019-109238GB-C22 funded by MICIU/AEI/ 10.13039/501100011033 and by “ERDF A way of making Europe” as well as by Ministry for Digital Transformation and Civil Service and ‘Next-GenerationEU’/PRTR under Grant TSI-100925-2023-1, and by the Xunta de Galicia (Grant ED431C 2022/44) with the European Union ERDF funds. CITIC, as Research Center accredited by Galician University System, is funded by “Consellería de Cultura, Educación e Universidade from Xunta de Galicia”, supported in an 80% through ERDF Operational Programme Galicia 2014–2020, and the remaining 20% by “Secretaría Xeral de Universidades” (Grant ED431G 2023/01)., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Dependency Graph Parsing as Sequence Labeling

  • Ezquerro, Ana
  • Vilares, David
  • Gómez-Rodríguez, Carlos
Presented at: Conference on Empirical Methods in Natural Language Processing, Miami, Florida, USA,12-16 Nov. 2024, Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License., [Abstract]: Various linearizations have been proposed to cast syntactic dependency parsing as sequence labeling. However, these approaches do not support more complex graph-based representations, such as semantic dependencies or enhanced universal dependencies, as they cannot handle reentrancy or cycles. By extending them, we define a range of unbounded and bounded linearizations that can be used to cast graph parsing as a tagging task, enlarging the toolbox of problems that can be solved under this paradigm. Experimental results on semantic dependency and enhanced UD parsing show that with a good choice of encoding, sequence-labeling semantic dependency parsers combine high efficiency with accuracies close to the state of the art, in spite of their simplicity., We acknowledge the European Research Council (ERC), which has funded this research under the Horizon Europe research and innovation programme (SALSA, grant agreement No 101100615). We also acknowledge grants SCANNER-UDC (PID2020-113230RB-C21) funded by MICIU/AEI/10.13039/501100011033; GAP (PID2022-139308OA-I00) funded by MICIU/AEI/10.13039/501100011033/ and ERDF, EU; LATCHING (PID2023-147129OB-C21) funded by MICIU/AEI/10.13039/501100011033 and ERDF, EU; and TSI-100925-2023-1 funded by Ministry for Digital Transformation and Civil Service and “NextGenerationEU” PRTR; as well as funding by Xunta de Galicia (ED431C 2024/02), and Centro de Investigación de Galicia “CITIC”, funded by the Xunta de Galicia through the collaboration agreement between the Consellería de Cultura, Educación, Formación Profesional e Universidades and the Galician universities for the reinforcement of the research centres of the Galician University System (CIGUS)., Xunta de Galicia; ED431C 2024/02