DI - LABDA - Comunicaciones en Congresos y otros eventos

Permanent URI for this collection

http://dspace.uc3m.es/handle/10016/8041

Browse

Now showing 1 - 20 of 81

Disambiguating Clinical Abbreviations using Pre-trained Word Embeddings
(SciTePress, 2021-02-11) Jaber, Areej Mustafa Mahmoud; Martínez Fernández, Paloma
Subscription video on demand (SVOD) platform accessibility verification method
(Springer Nature Limited, 2021-10-02) López Sánchez, Gema; Utray Delgado, Francisco
APEINTA: uso de nuevas tecnologías para facilitar el acceso a la educación para tod@s
(2011-04-08) Iglesias Maqueda, Ana María
An Ontology for formal representation of Drug Drug Interaction Knowledge
(2013-04) Herrero Zazo, María; Segura-Bedmar, Isabel; Martínez Fernández, Paloma
Ontologies are useful tools in text miming reserach tasks as a source of specialized vocabulary of terms and relationships in a given domain. Furthermore, formal knowledge representation propvieded by ontologies can be applied for new knowledge inference, wich can be exploited for biomedical research purposes. Drug-drug interactions (DDIs) are common adverse drug ractions having an important impact on patient safety and healthcare cost.
Is Moodle Accessible for Visually Impaired People?
(Springer, 2012) Calvo, Rocío; Iglesias Maqueda, Ana María; Moreno López, Lourdes
Most educational centers are currently using e-learning tools to provide the pedagogical resources for the students, especially in higher education. Nevertheless, some students are not able to access to this information because these authoring tools are not as accessible as they should be. The main aim of this paper is to evaluate if one of the most widely e-learning tool used around the world, Moodle, is accessible for visually impaired people. The evaluation shows that the accessibility guidelines provided by the World Wide Web Consortium (W3C) are not accomplished by the tool. Moreover, it shows that people using screen readers are not able to access to the majority of the functionality of Moodle.
An Approach to Circumstantial Knowledge Management for Human-Like Interaction
(SCITEPRESS (Science and Technology Publications,Lda.), 2014) Baldominos Gómez, Alejandro; Calle Gómez, Francisco Javier; Cuadra Fernández, María Dolores
This paper proposes the design of a general-purpose domain-independent knowledge model formalizing and managing the circumstantial knowledge involved in the human interaction process, i.e., a Situation Model. Its design is aimed to be embodied into a human-like interaction system, thus enriching the quality of the interaction by providing context-aware features to the interaction system. The proposal differs from similar work in that it is supported by the spatio-temporal databases technology. Additionally, since the proposed model requires to be fed with real knowledge obtained from each specific interaction domain, this paper also proposes an edition tool for acquiring and managing that circumstantial knowledge. The tool also supports the simulation over the model to check the correctness and completeness of the acquired knowledge. Finally, some scenario examples are provided in order to illustrate how the Situation Model works, and to gain perspective on its future possibilities of application in different systems where context-aware services can make a difference.
Combining Similarities with Regression based Classiffiers for Entity Linking at TAC 2010
(National Institute of Standards And Technology, 2010-11) Pablo-Sánchez, César de; Perea Moraleda, Juan Ignacio; Martínez Fernández, Paloma
The UC3M team has sent three runs for each Entity Linking task proposed in the Knowledge Base Population (KBP) track at TAC 2010. The skeleton system presented in 2009 has evolved in 2010 by incor- porating some new tools, new algorithms for candidate retrieval and feature extraction, and two new stages that use regression based clas- si ers for candidate ltering. These improvements have allowed the UC3M team overall values to almost reach the median values of all participants in the Entity Linking tasks.
Requisitos de accesibilidad web en los reproductores multimedia
(Ibergarceta, 2011-09) González, María; Moreno López, Lourdes; Martínez Fernández, Paloma; Iglesias Maqueda, Ana María
El contenido de vídeo se ha ido incorporando en la Web sin tener en mente las barreras de accesibilidad que pueden llegar a incorporar si no se hace de forma adecuada. Dado su gran aumento, es fundamental dar un cambio de rumbo, y empezar a incluir contenido de vídeo que cumpla los requisitos de accesibilidad necesarios para que puedan acceder a él el mayor número de usuarios posible. En la interacción del usuario con la reproducción de un vídeo intervienen muchos aspectos, siendo de gran importancia el agente de usuario web (navegadores, reproductores, etc.). A través de los reproductores multimedia los usuarios acceden a los contenidos de tipo vídeo, por lo que es fundamental que éstos cumplan un mínimo de requisitos de accesibilidad. En este artículo se presentan estándares, normativa y buenas prácticas relativas, así como una propuesta de método ágil de evaluación de los requisitos de accesibilidad en un reproductor multimedia. Por último, como un recurso a profesionales que quieran incluir reproductores multimedia accesibles en sus sitios web, se proporcionan unas guías básicas.
Conocimiento circunstancial en sistemas de interacción natural
(Thomson, 2007-09) Valle Agudo, David del; Rivero Espinosa, Jessica; Cuadra Fernández, María Dolores; Calle Gómez, Francisco Javier
El trabajo presentado en este artículo se centra en la gestión del conocimiento circunstancial para mejorar los aspectos relacionados con la interacción natural. En primer lugar se presenta la arquitectura cognitiva, marco que sustenta el sistema de interacción. Esta arquitectura está compuesta de distintos modelos (de funcionamiento autónomo) cuya implementación se basa en sistemas multi-agente. Por último se presenta una primera aproximación del modelo de situación, uno de los componentes más relevantes del sistema, para la gestión de la circunstancia de la interacción.
Overlapping Chat's Accessibility Requirements between students with and without disabilities due to the mobile limitations
(International Association for Development of The Information Society, 2014-02) Calvo, Rocío; Iglesias Maqueda, Ana María; Moreno López, Lourdes
The use of Chats has been extended for mobile-learning (m-learning) environments in the last decade. Students and teachers can communicate in real time and they do not need to wait till their next tutoring date. However, Chats have many accessibility barriers and many students cannot use this collaborative tool. These accessibility barriers affect students with disabilities but students without disabilities can face the same accessibility problems too due to the restrictions and limitations of handheld devices. Previous studies have improved the accessibility of Chats for a specific environment or disabilities but none of them is focused on the limitations that students without disabilities can face when they are using Chats in handheld devices. This is the main aim of this research; specify how the Chats' accessible requirements have been elicited and analyze the benefits that obtained requirements can produce for people without disabilities in m-learning contexts.
Are Passages Enough? The MIRACLE Team Participation at QA@CLEF2009
(Springer, 2009-09) Vicente-Díez, María Teresa; Pablo-Sánchez, César de; Martínez Fernández, Paloma; Moreno Schneider, Julián; Garrote Salazar, Marta
This paper summarizes the participation of the MIRACLE team in the Multilingual Question Answering Track at CLEF 2009. In this campaign, we took part in the monolingual Spanish task at ResPubliQA and submitted two runs. We have adapted our QA system to the new JRC-Acquis collection and the legal domain. We tested the use of answer filtering and ranking techniques against a baseline system using passage retrieval with no success. The run using question analysis and passage retrieval obtained a global accuracy of 0.33, while the addition of an answer filtering resulted in 0.29. We provide an analy-sis of the results for different questions types to investigate why it is difficult to leverage previous QA techniques. Another task of our work has been the appli-cation of temporal management to QA. Finally we include some discussion of the problems found with the new collection and the complexities of the domain.
SemEval-2013 Task 9 : Extraction of Drug-Drug Interactions from Biomedical Texts (DDIExtraction 2013)
(Association for Computational Linguistics, 2013-06) Segura-Bedmar, Isabel; Martínez Fernández, Paloma; Herrero Zazo, María
The DDIExtraction 2013 task concerns the recognition of drugs and extraction of drugdrug interactions that appear in biomedical literature. We propose two subtasks for the DDIExtraction 2013 Shared Task challenge: 1) the recognition and classification of drug names and 2) the extraction and classification of their interactions. Both subtasks have been very successful in participation and results. There were 14 teams who submitted a total of 38 runs. The best result reported for the first subtask was F1 of 71.5% and 65.1% for the second one.
UEM-UC3M: An Ontology-based named entity recognition system for biomedical texts
(Association for Computational Linguistics, 2015-06) Sánchez Cisneros, Daniel; Aparicio Gali, Fernando
Drug name entity recognition focuses on identifying concepts appearing in the text that correspond to a chemical substance used in pharmacology for treatment, cure, prevention or diagnosis of diseases. This paper describes a system based on ontologies for identifying the chemical substances in biomedical text. The system achieves an F-1 measure of 0.529 in the task.
UC3M: A kernel-based approach to identify and classify DDIs in biomedical texts
(Association for Computational Linguistics, 2013-06) Sánchez Cisneros, Daniel
The domain of DDI identification is constantly showing a rise of interest from scientific community since it represents a decrease of time and healthcare cost. In this paper we purpose a new approach based on shallow linguistic kernel methods to identify DDIs in biomedical manuscripts. The approach outlines a first step in the usage of semantic information for DDI identification. The system obtained an F1 measure of 0.534.
An ontology for drug-drug interactions
(CEUR, 2014-01) Herrero Zazo, María; Hastings, Janna; Segura-Bedmar, Isabel; Croset, Samuel; Martínez Fernández, Paloma; Steinbeck, Christoph
Drug-drug interactions form a significant risk group for adverse effects associ-ated with pharmaceutical treatment. These interactions are often reported in the literature, however, they are sparsely represented in machine-readable re-sources, such as online databases, thesauri or ontologies. These knowledge sources play a pivotal role in Natural Language Processing (NLP) systems since they provide a knowledge representation about the world or a particular do-main. While ontologies for drugs and their effects have proliferated in recent years, there is no ontology capable of describing and categorizing drug-drug in-teractions. Moreover, there is no artifact that represents all the possible mecha-nisms that can lead to a DDI. To fill this gap we propose DINTO, an ontology for drug-drug interactions and their mechanisms. In this paper we describe the classes, relationships and overall structure of DINTO. The ontology is free for use and available at https://code.google.com/p/dinto/
UC3M system: Determining the Extent, Type and Value of Time Expressions in TempEval-2
(Association for Computational Linguistics, 2010-07) Vicente-Díez, María Teresa; Moreno Schneider, Julián; Martínez Fernández, Paloma
This paper describes the participation of Universidad Carlos III de Madrid in Task A of the TempEval-2 evaluation. The UC3M system was originally developed for the temporal expressions recognition and normalization (TERN task) in Spanish texts, according to the TIDES standard. Current version supposes an almost-total refactoring of the earliest system. Additionally, it has been adapted to the TimeML annotation schema and a considerable effort has been done with the aim of increasing its coverage. It takes a rule-based design both in the identification and the resolution phases. It adopts an inductive approach based on the empirical study of frequency of temporal expressions in Spanish corpora. Detecting the extent of the temporal expressions the system achieved a Precision/Recall of 0.90/0.87 whereas, in determining the TYPE and VALUE of those expressions, system results were 0.91 and 0.83, respectively.
Temporal information needs in ResPubliQA: an attempt to improve accuracy. The UC3M Participation at CLEF 2010
(2010-09) Vicente-Díez, María Teresa; Moreno Schneider, Julián; Martínez Fernández, Paloma
The UC3M team participates in 2010 in the second ResPubliQA evaluation campaign taking part in the monolingual Spanish task. On this occasion we have completely redesigned our Question Answering system, product of multiple efforts while being part of the MIRACLE team, by creating a whole new architecture. The aim was to gain in modularity, flexibility and evaluation capabilities that previous versions left pending. Despite its initial open-domain philosophy, the new system was tested by means of the JRCAcquis and EUROPARL collections on the legal domain. We submitted two runs for the participation in the paragraph selection task. The main attempts in this campaign have focused on the study of the information needs concerning time. Starting from implementing a base system based on passage retrieval, we added temporal question analysis capabilities, temporal indexing to the collection, as well as some temporal filtering and reasoning features, getting a global accuracy of 0.51. In the second run we have implemented an answer analysis module based on n-gram analysis. The obtained results are slightly better, achieving a 0.52. We discuss the results found from each configuration when applied to the different temporal questions types.
Some Experiments in Evaluating ASR Systems Applied to Multimedia Retrieval
(Springer, 2009-09) Moreno Schneider, Julián; Garrote Salazar, Marta; Martínez Fernández, Paloma; Martínez Fernández, José Luis
This paper describes some tests performed on different types of voice/audio input applying three commercial speech recognition tools. Three multimedia retrieval scenarios are considered: a question answering system, an automatic transcription of audio from video files and a real-time captioning system used in the classroom for deaf students. A software tool, RET (Recognition Evaluation Tool), has been developed to test the output of commercial ASR systems.
Combining Syntactic Information and Domain-Specific Lexical Patterns to Extract Drug-Drug Interactions from Biomedical Texts
(ACM, 2010-10) Segura-Bedmar, Isabel; Martínez Fernández, Paloma; Pablo-Sánchez, César de
A drug-drug interaction (DDI) occurs when one drug influences the level or activity of another drug. The increasing volume of the scientific literature overwhelms health care professionals trying to be kept up-to-date with all published studies on DDI. Information Extraction (IE) techniques can provide an interesting way of reducing the time spent by health care professionals on reviewing the literature. Nevertheless, no approach has been carried out to extract DDI from texts. To the best of our knowledge, this work proposes the first integral solution for the automatic extraction of DDI from biomedical texts.
A Bio-Inspired Algorithm for Searching Relationships in Social Networks
(IEEE - The Institute Of Electrical And Electronics Engineers, Inc, 2011-10) Rivero Espinosa, Jessica; Cuadra Fernández, María Dolores; Calle Gómez, Francisco Javier; Isasi, Pedro
Nowadays the Social Networks are experiencing a growing importance. The reason of this is that they enable the information exchange among people, meeting people in the same field of work or establishing collaborations with other research groups. In order to manage social networks and to find people inside them, they are usually represented as graphs with persons as nodes and relationships between them as edges. Once this is done, establishing contact with anyone involves searching the chain of people to reach him/her, that is, the search of the path inside the graph which joins two nodes. In this paper, a new algorithm based on nature is proposed to realize this search: SoS-ACO (Sense of Smell - Ant Colony Optimization). This algorithm improves the classical ACO algorithm when it is applied in huge graphs.

Browse

Recent Submissions