A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is
This work presents the development of a portable, wireless activity monitoring system for the estimation of biomechanical gait parameters. The system uses a pair of instrumented insoles able to measure pressure from different points of the foot including four commercial piezoresistive pressure sensors and a three-axis accelerometer, all together integrated in the insole to determine foot forces during stance and swing phases. The system allows to analyse the data with a RF communications to a computer or reading from SD memory card.dblp:conf/iwbbio/MartiDJGMR13 fatcat:bqnfrautxvc4bdbkzmd4blf5wq
Over a period of almost four decades, the monk parakeet has been successful in establishing and dispersing in urban Santiago, although little is known about its potential impact. ... They were first released by private citizens in eastern Santiago in 1972 (IRIARTE et al., 2005) . ... Ectoparasites and endoparasites found in adult monk parakeets monachus) caught in Santiago, Chile. ...doi:10.1590/s1984-29612017023 pmid:28746442 fatcat:f6r5pl6oyzggdcdy3yxhegahh4
This document describes the participation of the SINAI Research Group in the 6 th challenge on Recognition of Textual Entailment (RTE). Our approach is a supervised one, by applying a learning process on the development data. The model trained was a stacking of two SVM models, each one over different attributes. One of the SVMs was trained on the distance between Personalized Page Rank vectors, and the other on Named Entities matching counts. The results obtained are low, mainly due to thedblp:conf/tac/Montejo-RaezPSL10 fatcat:2rkbq5dy3jemnm3p3dctkingva
more »... icity of the system. In any case, the use of stacking for merging different features results in a relevant increment in performance.
Our research aim is twofold: the first one is to get leverage from the relevance feedback that the user provides over the course of every search session. In this way, we explore PIR task as a text categorization problem in order to distinguish between relevant and not relevant documents for the given user. A number of supervised machine learning algorithms has been applied in order to accomplish this task. The second one is related to implicit feedback. More concisely, time spent readingdblp:conf/clef/Andreu-MarinSLD18 fatcat:rersevycabh57epzigx3hgckqe
more »... ts and text complexity. From the point of view of text complexity, we propose the hypothesis that there are significant differences of perplexity between judged/non-judged documents by the user. We find some weak statistical evidence that points out that high perplexity and judged documents are correlated.
This document describes the participation of the SINAI Research Group in the 7 th challenge on Recognition of Textual Entailment (RTE). Our approach extends the promising results obtained in the last campaing into a well know framework for textual entailment recognition known as EDITS. Although the proposed solution is modest, results encourage us in the use of Personalized Page Rank as a technique for generating weighted vectors of synsets per term in texts and applying distance metrics todblp:conf/tac/Montejo-RaezSOL11 fatcat:sgph7wpk6rga3ll7tkovi5jgei
more »... ute a value of lexical similarity between terms found in hypotheses and those in candidate texts.
The online reputation management systems help to the consumers to make buying decisions looking for opinions in the web about many products offered by companies, also interested in the same opinions. This paper presents the system developed by the SINAI research group at the WEPS-3 task, called Online Reputation Management. Given a Twitter entry and a company name, the goal is to decide if the entry talks about this company. Our system is based on the use of linguistic information in Twittersdblp:conf/clef/CumbrerasVSP10 fatcat:wghrntxdnffhvdp5vy6oqk7sb4
more »... tries for extracting information and creating an XML data collection about companies referred in the Twitter entries. This XML collection is filled extracting information from Internet web pages, like Wikipedia, and the use of the DBpedia ontology. Using this collection and some logical rules we have developed a promising system, with a very good precision and easily extensible with the addition of new rules and other Internet resources.
This paper describes the rst participation of the SINAI (Intelligent Systems of Access Information) group of the University of Jaén in the AVE task of QA@CLEF 2007. We have developed a system made up of training and classication processes, that uses machine learning methods (bbr, timbl). Based on lexical features it obtains good results, a 41% of QA accuracy.dblp:conf/clef/CumbrerasOSL07 fatcat:ctw37wbhk5dyddyfj25jxb6jga
Resumen: Presentamos una plataforma web que constituye una herramienta para poder evaluar la comprensión lectora a través de dos experimentos: un test de fluidez lectora que permitirá inferir el grado de fluidez lectora del participante y un sistema de recuperación de información interactivo, donde el participante explorará y evaluará un conjunto de documentos como relevantes o no relevantes. La cuestión que se plantea es la incidencia del nivel de fluidez lectora en la búsqueda de información.dblp:journals/pdln/CasaSCD19 fatcat:6m4mwqpw4fgu7iavlkpbnmbis4
more »... Palabras clave: Comprensión y fluidez lectora, recuperación de información interactiva Abstract: We present a web platform that constitutes a tool to evaluate reading comprehension through two experiments: a reading fluency test that will allow inferring the degree of participant's reading fluency and an interactive information retrieval system where the participant will explore and evaluate a set of documents as relevant or not relevant. The question to be answered is the impact of the level of reading fluency regarding with performance in tasks of searching for information.
gracias a la integración, con requisitos de tiempo de respuesta y alta disponibilidad, de ontologías médicas, técnicas de análisis de texto, reconocimiento de entidades y búsqueda de información sobre fuentes diversas externas. El resultado es una aplicación intuitiva y a la vez potente, que permite identificar la terminología médica sobre cualquier texto con un solo "click". Sobre ese reconocimiento, se permite filtrado de sentidos y subconceptos y la recuperación de información sobre recursosdblp:journals/pdln/Lopez-UbedaDMSA18 fatcat:hwlqboeyczaohdf2bdqrvkpo24
more »... como SciELO, Google Scholar y Medline. Además, el sistema genera un grafo conceptual de manera automática, que permite relacionar semánticamente los términos que aparecen en el texto. Palabras clave: reconocimiento automático de entidades, ontologías, terminología médica, informes médicos, recuperación de información, UMLS
For the EXIST 2021 sexism detection task, a novel approach is proposed. In previous work we see that deep learning models capture biases related to race, gender, religion, etc. There are numerous works that seek to lower the bias of these models to make them fairer and more equitable. We will use the opposite approach to these works, instead of reducing the bias of the models we will seek to increase it. So we will train 3 times the same base model, generating 3 versions of the model. A normaldblp:conf/sepln/Garrido-MunozMS21 fatcat:oxfqfzzaargixporatsvj4rsyy
more »... ersion, a sexist version and an anti-sexist version. Belonging to these models will mean marking or not the tweet as sexist.
In addition, acknowledging the support of technical staff such as Ulises Serrano, Francisco Agulló and Javier Fernández from the University of Alicante. ...dblp:conf/tac/GutierrezMTMMMZ16 fatcat:7joopslzcvhjnciiedhfybg56m
sourceforge.net/projects/arasuite/ 3 http://scaut.ugr.es/scaut/ 4 http://prezi.com/jcpr9qcmcnr-/cpa/ 5 http://fundacionorange.es/emintza.html Ontologías SUpO y PictOntology SUpO (Simple Upper Ontology)(Martínez-Santiago ...dblp:journals/pdln/CumbrerasSRDV16 fatcat:ybgxss6ivfbpvn6e476fbfu7m4
Resumen Crear un corpus extraído a partir de la Web está lejos de ser una tarea trivial. El elevado grado de heterogeneidad que es usual encontrar en el formato HTML, la gran cantidad de información irrelevante tanto en el sitio Web como dentro de una misma página y otros problemas de diversa índole, dificultan la obtención de un conjunto de documentos de aspecto homogéneo, estructurado y libre de ruido. Es presentada aquí una herramienta que pretende no sólo recuperar y almacenardblp:journals/pdln/SantiagoUV01 fatcat:bk7xxiv5trb33ffmtymisxda5a
more »... determinados sitios Web, sino dotar a los documentos obtenidos de un formato conveniente y homogéneo para su procesamiento automático, con independencia del origen de cada documento.
The aim for SINAI group is twofold in the task of belief classification for English. On one hand, we continue with the development of a hierarchical Bayesian model as a formalism to describe and classify categories, and its comparison with other popular classification algorithms. On the other hand, since the belief-sentiment annotation guidelines highlight the leverage of modal verbs, firstly, we have studied the distribution of this verbs over the corpus and, secondly, those events anddblp:conf/tac/Blanco-LopezSM17 fatcat:xubjxhvdfrh35kldlli72fakae
more »... s that are under the scope of a modal verb have been accordingly labelled. We have found that this issue does not increase the performance of the classifiers. Since we have found that the scope of modal verbs and the category of the corresponding facts are correlated, it is necesary a more in-depth analysis of the results and possibly a more fine-grained classification of modal verbs. For example, by making explicit the distinction between deontinc and epistemic senses of such verbs.
« Previous Showing results 1 — 15 out of 8,471 results