Persona: Araujo Serna, M. Lourdes
Cargando...
Dirección de correo electrónico
ORCID
0000-0002-7657-4794
Fecha de nacimiento
Proyectos de investigación
Unidades organizativas
Puesto de trabajo
Apellidos
Araujo Serna
Nombre de pila
M. Lourdes
Nombre
22 resultados
Resultados de la búsqueda
Mostrando 1 - 10 de 22
Publicación Anonimización de Informes Médicos(Universidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Inteligencia Artificial, 2021-09-15) Gaitán Rivas, José Antonio; Araujo Serna, M. Lourdes; Martínez, RaquelCon el objetivo de mejorar la salud y seguridad de los pacientes cada vez existe un mayor interés en gestionar eficientemente el contenido de los historiales clínicos electrónicos. Dichos informes médicos están escritos principalmente en lenguaje natural, por lo que contienen información no estructurada generalizadamente, haciéndose imprescindibles tecnologías de Minería de Textos y de PLN (Procesamiento de Lenguaje Natural) para su explotación. Con técnicas apropiadas de dichas tecnologías se ayuda en la toma de decisiones clínicas o se facilita la reutilización de medicamentos, entre muchas otras ventajas. Sin embargo, los registros clínicos con información de salud protegida (PHI o Protected Health Information) no pueden ser compartidos directamente debido a restricciones relacionadas con la protección de datos sobre dicha información privada de los pacientes. Es necesaria pues, una anonimización o disociación de dichos registros antes de poder ser usados externamente, debiéndose eliminar total o parcialmente toda información que permita identificar al paciente. La base del presente trabajo ha sido la tarea de evaluación MEDDOCAN (Medical Document Anonymization), a la que puede accederse en https://temu.bsc.es/meddocan , que forma parte de la iniciativa IberLEF 2019, y con la que se organizó un desafío para la comunidad hispano-hablante, con el objetivo de diseñar sistemas eficientes de anonimización de documentos médicos escritos en español. La tarea de MEDDOCAN se estructura en dos subtareas: Identificación y clasificación de entidades (nombres de paciente, teléfonos, etc.) Detección de texto sensible La evaluación oficial de la tarea, por tanto, engloba los resultados de ambas subtareas. El corpus está formado por 1.000 estudios de casos clínicos, y cada uno de ellos cuenta, de forma anexa, con expresiones PHI realizadas por profesionales. 4 Del total de 1.000 casos, se reservó el 50% (500 casos) para entrenamiento de la tarea, un 25% (250 casos) para labores de desarrollo, y el otro 25% (250 casos) para pruebas. En el desafío participaron 18 equipos, de un total de 8 nacionalidades distintas, y el mejor resultado, basado en la métrica F-score, fue de 0.9360 para la subtarea 1 (“Identificación y clasificación de entidades”) y de 0.9611 para la subtarea 2 (“Detección de texto sensible”). A lo largo del presente trabajo estudiaremos y compararemos los datos proporcionados por los organizadores de la tarea, y propondremos un sistema que implementa una solución simple mediante técnicas de Aprendizaje Automático y Minería de Textos. Finalmente analizaremos los resultados obtenidos con dicho sistema y serán comparados con los de los participantes en la tarea, exponiendo las ventajas e inconvenientes para la arquitectura escogida, respecto a las presentadas. En dichas conclusiones incorporaremos un listado de posibles mejoras o implementaciones futuras recomendadas para mejorar el rendimiento.Publicación Identifying patterns for unsupervised grammar induction(2010-07-15) Santamaría Martínez de la Casa, Jesús; Araujo Serna, M. LourdesThis paper describes a new method for unsupervised grammar induction based on the automatic extraction of certain patterns in the texts. Our starting hypothesis is that there exist some classes of words that function as separators, marking the beginning or the end of new constituents. Among these separators we distinguish those which trigger new levels in the parse tree. If we are able to detect these separators we can follow a very simple procedure to identify the constituents of a sentence by taking the classes of words between separators. This paper is devoted to describe the process that we have followed to automatically identify the set of separators from a corpus only annotated with Part-of-Speech (POS) tags. The proposed approach has allowed us to improve the results of previous proposals when parsing sentences fromtheWall Street Journal corpus.Publicación Analyzing information retrieval methods to recover broken web links(2011-06-19) Martínez Romo, Juan; Araujo Serna, M. LourdesIn this work we compare different techniques to automatically find candidate web pages to substitute broken links. We extract information from the anchor text, the content of the page containing the link, and the cache page in some digital library.The selected information is processed and submitted to a search engine. We have compared different information retrievalmethods for both, the selection of terms used to construct the queries submitted to the search engine, and the ranking of the candidate pages that it provides, in order to help the user to find the best replacement. In particular, we have used term frequencies, and a language model approach for the selection of terms; and cooccurrence measures and a language model approach for ranking the final results. To test the different methods, we have also defined a methodology which does not require the user judgments, what increases the objectivity of the results.Publicación Semi‑supervised incremental learning with few examples for discovering medical association rules(BioMed Central, 2022) Sánchez‑de‑Madariaga, Ricardo; Cantero Escribano, José Miguel; Martínez Romo, Juan; Araujo Serna, M. LourdesBackground: Association Rules are one of the main ways to represent structural patterns underlying raw data. They represent dependencies between sets of observations contained in the data. The associations established by these rules are very useful in the medical domain, for example in the predictive health field. Classic algorithms for association rule mining give rise to huge amounts of possible rules that should be filtered in order to select those most likely to be true. Most of the proposed techniques for these tasks are unsupervised. However, the accuracy provided by unsupervised systems is limited. Conversely, resorting to annotated data for training supervised systems is expensive and time‑consuming. The purpose of this research is to design a new semi‑supervised algorithm that performs like supervised algorithms but uses an affordable amount of training data. Methods: In this work we propose a new semi‑supervised data mining model that combines unsupervised techniques (Fisher’s exact test) with limited supervision. Starting with a small seed of annotated data, the model improves results (F‑measure) obtained, using a fully supervised system (standard supervised ML algorithms). The idea is based on utilising the agreement between the predictions of the supervised system and those of the unsupervised techniques in a series of iterative steps. Results: The new semi‑supervised ML algorithm improves the results of supervised algorithms computed using the F‑measure in the task of mining medical association rules, but training with an affordable amount of manually annotated data. Conclusions: Using a small amount of annotated data (which is easily achievable) leads to results similar to those of a supervised system. The proposal may be an important step for the practical development of techniques for mining association rules and generating new valuable scientific medical knowledge.Publicación Generation of social network user profiles and their relationship with suicidal behaviour(Sociedad Española para el Procesamiento del Lenguaje Natural, 2024) Fernández Hernández, Jorge; Araujo Serna, M. Lourdes; Martínez Romo, JuanActualmente el suicidio es una de las principales causas de muerte en el mundo, por lo que poder caracterizar a personas con esta tendencia puede ayudar a prevenir posibles intentos de suicidio. En este trabajo se ha recopilado un corpus, llamado SuicidAttempt en español compuesto por usuarios con o sin menciones explícitas de intentos de suicidio, usando la aplicación de mensajería Telegram. Para cada uno de los usuarios se han anotado distintos rasgos demográficos de manera semi-automática mediante el empleo de distintos sistemas, en unos casos supervisados y en otros no supervisados. Por último se han analizado estos rasgos recogidos, junto con otros lingüísticos extraídos de los mensajes de los usuarios, para intentar caracterizar distintos grupos en base a su relación con el comportamiento suicida. Los resultados sugieren que la detección de estos rasgos demográficos y psicolingüísticos permiten caracterizar determinados grupos de riesgo y conocer en profundidad los perfiles que realizan dichos actos.Publicación Automatic Recommendation of Forum Threads and Reinforcement Activities in a Data Structure and Programming Course(MDPI, 2023-09-21) Plaza Morales, Laura; Araujo Serna, M. Lourdes; López Ostenero, Fernando; Martínez Romo, JuanOnline learning is quickly becoming a popular choice instead of traditional education. One of its key advantages lies in the flexibility it offers, allowing individuals to tailor their learning experiences to their unique schedules and commitments. Moreover, online learning enhances accessibility to education, breaking down geographical and economical boundaries. In this study, we propose the use of advanced natural language processing techniques to design and implement a recommender that supports e-learning students by tailoring materials and reinforcement activities to students’ needs. When a student posts a query in the course forum, our recommender system provides links to other discussion threads where related questions have been raised and additional activities to reinforce the study of topics that have been challenging. We have developed a content-based recommender that utilizes an algorithm capable of extracting key phrases, terms, and embeddings that describe the concepts in the student query and those present in other conversations and reinforcement activities with high precision. The recommender considers the similarity of the concepts extracted from the query and those covered in the course discussion forum and the exercise database to recommend the most relevant content for the student. Our results indicate that we can recommend both posts and activities with high precision (above 80%) using key phrases to represent the textual content. The primary contributions of this research are three. Firstly, it centers on a remarkably specialized and novel domain; secondly, it introduces an effective recommendation approach exclusively guided by the student’s query. Thirdly, the recommendations not only provide answers to immediate questions, but also encourage further learning through the recommendation of supplementary activities.Publicación A keyphrase-based approach for interpretable ICD-10 code classification of Spanish medical reports(Elsevier, 2021) Fabregat Marcos, Hermenegildo; Duque Fernández, Andrés; Araujo Serna, M. Lourdes; Martínez Romo, JuanBackground and objectives: The 10th version of International Classification of Diseases (ICD-10) codification system has been widely adopted by the health systems of many countries, including Spain. However, manual code assignment of Electronic Health Records (EHR) is a complex and time-consuming task that requires a great amount of specialised human resources. Therefore, several machine learning approaches are being proposed to assist in the assignment task. In this work we present an alternative system for automatically recommending ICD-10 codes to be assigned to EHRs. Methods: Our proposal is based on characterising ICD-10 codes by a set of keyphrases that represent them. These keyphrases do not only include those that have literally appeared in some EHR with the considered ICD-10 codes assigned, but also others that have been obtained by a statistical process able to capture expressions that have led the annotators to assign the code. Results: The result is an information model that allows to efficiently recommend codes to a new EHR based on their textual content. We explore an approach that proves to be competitive with other state-of-the-art approaches and can be combined with them to optimise results. Conclusions: In addition to its effectiveness, the recommendations of this method are easily interpretable since the phrases in an EHR leading to recommend an ICD-10 code are known. Moreover, the keyphrases associated with each ICD-10 code can be a valuable additional source of information for other approaches, such as machine learning techniques.Publicación Experimentación basada en deep learning para el reconocimiento del alcance y disparadores de la negación(Sociedad Española para el Procesamiento del Lenguaje Natural, 2019) Fabregat Marcos, Hermenegildo; Araujo Serna, M. Lourdes; Martínez Romo, JuanLa detección automática de los distintos elementos de la negación es un frecuente tema de estudio debido a su alto impacto en diversas tareas de procesamiento de lenguaje natural. Este articulo presenta un sistema basado en deep learning y de arquitectura no dependiente del idioma para la detección automática tanto de disparadores como del alcance de la negación para inglés y español. El sistema presentado obtiene para ingles resultados comparables a los obtenidos en recientes trabajos por sistemas más complejos. Para español destacan los resultados obtenidos en la detección de claves de negación. Por último, los resultados para el reconocimiento del alcance de la negación, son similares a los obtenidos en inglés.Publicación Discovering related scientific literature beyond semantic similarity: a new co-citation approach(Springer, 2019-05-17) Rodríguez Prieto, Oscar; Araujo Serna, M. Lourdes; Martínez Romo, JuanWe propose a new approach to recommend scientific literature, a domain in which the efficient organization and search of information is crucial. The proposed system relies on the hypothesis that two scientific articles are semantically related if they are co-cited more frequently than they would be by pure chance. This relationship can be quantified by the probability of co-citation, obtained from a null model that statistically defines what we consider pure chance. Looking for article pairs that minimize this probability, the system is able to recommend a ranking of articles in response to a given article. This system is included in the co-occurrence paradigm of the field. More specifically, it is based on co-cites so it can produce recommendations more focused on relatedness than on similarity. Evaluation has been performed on the ACL Anthology collection and on the DBLP dataset, and a new corpus has been compiled to evaluate the capacity of the proposal to find relationships beyond similarity. Results show that the system is able to provide, not only articles similar to the submitted one, but also articles presenting other kind of relations, thus providing diversity, i.e. connections to new topics.Publicación Can deep learning techniques improve classification performance of vandalism detection in Wikipedia?(Elsevier, 2019) Martinez-Rico, Juan R.; Martínez Romo, Juan; Araujo Serna, M. LourdesWikipedia is a free encyclopedia created as an international collaborative project. One of its peculiarities is that any user can edit its contents almost without restrictions, what has given rise to a phenomenon known as vandalism. Vandalism is any attempt that seeks to damage the integrity of the encyclopedia deliberately. To address this problem, in recent years several automatic detection systems and associated features have been developed. This work implements one of these systems, which uses three sets of new features based on different techniques. Specifically we study the applicability of a leading technology as deep learning to the problem of vandalism detection. The first set is obtained by expanding a list of vandal terms taking advantage of the existing semantic-similarity relations in word embeddings and deep neural networks. Deep learning techniques are applied to the second set of features, specifically Stacked Denoising Autoencoders (SDA), in order to reduce the dimensionality of a bag of words model obtained from a set of edits taken from Wikipedia. The last set uses graph-based ranking algorithms to generate a list of vandal terms from a vandalism corpus extracted from Wikipedia. These three sets of new features are evaluated separately as well as together to study their complementarity, improving the results in the state of the art. The system evaluation has been carried out on a corpus extracted from Wikipedia (WP_Vandal) as well as on another called PAN-WVC-2010 that was used in a vandalism detection competition held at CLEF conference.
- «
- 1 (current)
- 2
- 3
- »