Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 7
Encontrada(s) 1 página(s)

Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Automatic explanation of the classification of Spanish legal judgments in jurisdiction-dependent law categories with tree estimators

  • González González, Jaime
  • de Arriba Perez, Francisco
  • García Méndez, Silvia
  • Busto Castiñeira, Andrea
  • González Castaño, Francisco Javier
Automatic legal text classification systems have been proposed in the literature to address knowledge extraction from judgments and detect their aspects. However, most of these systems are black boxes even when their models are interpretable. This may raise concerns about their trustworthiness. Accordingly, this work contributes with a system combining Natural Language Processing (nlp) with Machine Learning (ml) to classify legal texts in an explainable manner. We analyze the features involved in the decision and the threshold bifurcation values of the decision paths of tree structures and present this information to the users in natural language. This is the first work on automatic analysis of legal texts combining nlp and ml along with Explainable Artificial Intelligence techniques to automatically make the models’ decisions understandable to end users. Furthermore, legal experts have validated our solution, and this knowledge has also been incorporated into the explanation process as “expert-in-the-loop” dictionaries. Experimental results on an annotated data set in law categories by jurisdiction demonstrate that our system yields competitive classification performance, with accuracy values well above 90%, and that its automatic explanations are easily understandable even to non-expert users., Xunta de Galicia | Ref. ED481B-2021-118, Xunta de Galicia | Ref. ED481B-2022-093, Xunta de Galicia | Ref. ED431C 2022/04, Ministerio de Ciencia e Innovación | Ref. TED2021-130824B-C21, Universidade de Vigo/CISUG
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Explainable cognitive decline detection in free dialogues with a machine learning approach based on pre-trained Large Language Models

  • de Arriba Perez, Francisco
  • García Méndez, Silvia
  • Otero Mosquera, Javier
  • González Castaño, Francisco Javier
Cognitive and neurological impairments are very common, but only a small proportion of affected individuals are diagnosed and treated, partly because of the high costs associated with frequent screening. Detecting pre-illness stages and analyzing the progression of neurological disorders through effective and efficient intelligent systems can be beneficial for timely diagnosis and early intervention. We propose using Large Language Models to extract features from free dialogues to detect cognitive decline. These features comprise high-level reasoning content-independent features (such as comprehension, decreased awareness, increased distraction, and memory problems). Our solution comprises (i) preprocessing, (ii) feature engineering via Natural Language Processing techniques and prompt engineering, (iii) feature analysis and selection to optimize performance, and (iv) classification, supported by automatic explainability. We also explore how to improve Chatgpt’s direct cognitive impairment prediction capabilities using the best features in our models. Evaluation metrics obtained endorse the effectiveness of a mixed approach combining feature extraction with Chatgpt and a specialized Machine Learning model to detect cognitive decline within free-form conversational dialogues with older adults. Ultimately, our work may facilitate the development of an inexpensive, non-invasive, and rapid means of detecting and explaining cognitive decline., Xunta de Galicia | Ref. ED481B-2021-118, Xunta de Galicia | Ref. ED481B-2022-093, Xunta de Galicia | Ref. ED431C 2022/04, Agencia Estatal de Investigación | Ref. TED2021-130824B-C21, Universidade de Vigo/CISUG
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Contribución de congreso (ConferenceOutput)

Transformer language model-based mobile learning solution for higher education

  • García Méndez, Silvia
  • de Arriba Perez, Francisco
  • González Castaño, Francisco Javier
Mobile learning or mLearning has become an essential tool in many fields in this digital era, among the ones educational training deserves special attention, that is, applied to both basic and higher education towards active, flexible, effective high-quality and continuous learning. However, despite the advances in Natural Language Processing techniques, mLearning still does not take full advantage of the great potential of the latter techniques. It is the case of the transformer language models distributed in chatbot form. Accordingly, this work presents a mLearning application based on OpenAI GPT-3 model, which enables user-friendly interactions. The proposed system was tested in two evaluation scenarios, and the experimental results endorse its appropriateness toward learning experience enhancement., Xunta de Galicia | Ref. ED481B-2021-118, Xunta de Galicia | Ref. ED481B-2022-093, Xunta de Galicia | Ref. ED431C 2022/04, Agencia Estatal de Investigación | Ref. TED2021-130824B-C21
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Explainable assessment of financial experts’ credibility by classifying social media forecasts and checking the predictions with actual market data

  • García Méndez, Silvia
  • de Arriba Perez, Francisco
  • González González, Jaime
  • González Castaño, Francisco Javier
Social media include diverse interaction metrics related to user popularity, the most evident example being the number of user followers. The latter has raised concerns about the credibility of the posts by the most popular creators. However, most existing approaches to assess credibility in social media strictly consider this problem a binary classification, often based on a priori information, without checking if actual real-world facts back the users’ comments. In addition, they do not provide automatic explanations of their predictions to foster their trustworthiness. In this work, we propose a credibility assessment solution for financial creators in social media that combines Natural Language Processing and Machine Learning. The reputation of the contributors is assessed by automatically classifying their forecasts on asset values by type and verifying these predictions with actual market data to approximate their probability of success. The outcome of this verification is a continuous credibility score instead of a binary result, an entirely novel contribution by this work. Moreover, social media metrics (i.e., user context) are exploited by calculating their correlation with the credibility rankings, providing insights on the interest of the end-users in financial posts and their forecasts (i.e., drop or rise). Finally, the system provides natural language explanations of its decisions based on a model-agnostic analysis of relevant features., Xunta de Galicia | Ref. ED481B-2021-118, Xunta de Galicia | Ref. ED481B-2022-093, Xunta de Galicia | Ref. ED431C 2022/04, Agencia Estatal de Investigación | Ref. TED2021-130824B-C21, Universidade de Vigo/CISUG
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Leveraging Random Forests explainability for predictive modeling of children's conduct problems: insights from individual and family factors

  • Romero, Estrella
  • González González, Jaime
  • Álvarez Voces, María
  • Costa Montenegro, Enrique
  • Díaz Vázquez, Beatriz
  • Busto Castiñeira, Andrea
  • Villar, Paula
  • López Romero, Laura
Conduct problems are among the most complex, impairing, and prevalent challenges affecting the mental health of children and adolescents. Due to their multifaceted nature, it is important to develop predictive models that capture the intricate interactions among contributing factors. This longitudinal study aims to: (1) evaluate the utility and effectiveness of Random Forest models for classifying children with varying levels of conduct problems, (2) analyze the interactions between individual and family variables in predicting high levels of conduct problems, and (3) determine the most relevant factors or combinations for accurate child classification. The sample was drawn from the ELISA study, and consisted of 1,352 children assessed twice within a 1-year frame. The use of Random Forest and its inherent structure allowed to identify subsets of variables with the capability of predicting Conduct Problems in children. This research demonstrates the effectiveness of integrating psychological insights with advanced computational techniques to address critical concerns in children's mental health, emphasizing the need for enhanced screening and tailored interventions., Agencia Estatal de Investigación | Ref. TED2021-130824B-C21, Agencia Estatal de Investigación | Ref. TED2021-130824B-C22, Agencia Estatal de Investigación | Ref. PID2019-107897RB-I00, Xunta de Galicia | Ref. ED431C 2022/17, Xunta de Galicia | Ref. ED481A 2023/090, Agencia Estatal de Investigación | Ref. FPU21/00552, Agencia Estatal de Investigación | Ref. FPU22/02200, Agencia Estatal de Investigación | Ref. FPU21/00798, Agencia Estatal de Investigación | Ref. RYC2021-032890-I
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Adaptation of Augmentative and Alternative Communicators through the study of interactions with high-tech solution users

  • González González, Jaime
  • Costa Montenegro, Enrique
  • García Doval, Fátima María
  • Lopez Bravo, Cristina
  • de Arriba Perez, Francisco
Augmentative and Alternative Communication (aac) strategies ease communication tasks for people who require accessible solutions. These strategies are usually addressed by technological solutions such as mobile applications. This research seeks clues on the development of such applications by analyzing user interactions with Android application PictoDroid Lite, an aac communicator. This study considered a data set containing more than 85,000 interactions of users from more than 50 countries. The goal was to identify the primary needs reflected in the users’ behavior and how these applications handle them, providing other researchers and developers with relevant information about how users interact with these applications. We detected areas of improvement regarding the adaptation to users’ needs in terms of profiling, smart suggestions, and time habits., Xunta de Galicia | Ref. ED481A-2023-090, Xunta de Galicia | Ref. ED481B-2022-093, Xunta de Galicia | Ref. ED431C 2022/04, Agencia Estatal de Investigación | Ref. TED2021-130824B-C21
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Predictability and causality in spanish and english natural language generation

  • Busto Castiñeira, Andrea
  • González Castaño, Francisco Javier
  • García Méndez, Silvia
  • de Arriba Perez, Francisco
In recent years, the field of Natural Language Generation (NLG) has been boosted by the recent advances in deep learning technologies. Nonetheless, these new data-intensive methods introduce language-dependent disparities in NLG as the main training data sets are in English. Also, most neural NLG systems use decoder-only (causal) transformer language models, which work well for English, but were not designed with other languages in mind. In this work we depart from the hypothesis that they may introduce generation bias in target languages with less rigid word ordering, subject omission, or different attachment preferences for relative clauses, so that for these target languages other language generation strategies may be more desirable. This paper first compares causal and non-causal language modeling for English and Spanish, two languages with different grammatical structures and over 1.5 billion and 0.5 billion speakers, respectively. For this purpose, we define a novel metric of average causal and non-causal context-conditioned entropy of the grammatical category distribution for both languages as an information-theoretic a priori approach. The evaluation of natural text sources (such as training data) in both languages reveals lower average non-causal conditional entropy in Spanish and lower causal conditional entropy in English. According to this experiment, Spanish is more predictable than English given a non-causal context. Then, by applying a conditional relative entropy metric to text generation experiments, we obtain as insights that the best performance is respectively achieved with causal NLG in English, and with non-causal NLG in Spanish. These insights support further research in NLG in Spanish using bidirectional transformer language models., Xunta de Galicia | Ref. ED481B-2021-118, Xunta de Galicia | Ref. ED481B-2022-093, Xunta de Galicia | Ref. ED431C 2022/04, Agencia Estatal de Investigación | Ref. FPU21/00798, Agencia Estatal de Investigación | Ref. TED2021-130824B-C21