Skip to main content

Jorge Morato

Universidad Carlos III de Madrid, Computer Science, Faculty Member

Followers

284

Following

41

Co-authors

26

Public Views

I am currently a professor of Information Science in the Department of Computer Science at the Carlos III University of Madrid (Spain). I obtained a PhD in Library Science from the Carlos III University in 1999 on the subject of Knowledge Information Systems and its relationships with linguistics. From 1991-1999, I had grants and contracts from the Spanish National Research Council.My current research activity is centered on text mining, information extraction and pattern recognition, NLP, information retrieval, Web positioning, and Knowledge Organization Systems. I have published mainly on semi-automatic construction of thesauri and ontologies, topic maps, and conceptual and contextualized retrieval of semantic documents. My last projects deal with Semantic Metadata Interoperability and Search (SEMSE) and LIS training.I have taught courses on Information Retrieval, Search Engine Optimization, Software Engineering, and Knowledge Modelling Techniques and Management Systems. Some of them are published in the OpenCourseWare project
Address: University Carlos III
Dep. Computer Science
Avda. Universidad, 30
28911 Leganés
Madrid- Spain

less

Harvard University

National University of "Kyiv-Mohyla Academy"

European University Institute

Vinicius Garcia

Universidade Federal de Pernambuco

Visvesvaraya Technological University

Dr. Muhammad Rafiq

University of the Punjab

University of the Punjab

Kansas State University

Ramesh Chander Sharma

Ambedkar University Delhi

University of Cologne

InterestsView All (15)

Uploads

Books by Jorge Morato

glossariumBITri: Interdisciplinary Elucidation of Concepts, Metaphors, Theories and Problems Concerning INFORMATION - 2nd Edition

by Jose Maria Diaz Nafria, Francisco Salto Alemany, Juan Miguel Aguado, Gordana Dodig-Crnkovic, M. Burgin, Manuel Campos-Havidich, Roberto Gejman, Jorge Morato, Rosa Macarro, and Blanca Bravo

The glossariumBITri, planned as a central activity for the interdisciplinary study of information... more The glossariumBITri, planned as a central activity for the interdisciplinary study of information, developed by BITrum group in cooperation with the University of Santa Elena (Ecuador), essentially aims at serving as a tool for the clarification of concepts, theories and problems concerning information. Intending to embrace the most relevant points of view with respect to information, it is interdisciplinarily developed by a board of experts coming from a wide variety of scientific fields. The glossariumBITri kindly invites the scientific community to make contributions of any kind aimed at clarifying in the field of information studies.

Análisis de relaciones cienciométricas y lingüisticas en un entorno automatizado

Se presenta una visión integradora de las diferentes herramientas que permiten el estudio de las ... more Se presenta una visión integradora de las diferentes herramientas que permiten el estudio de las conexiones entre documentos, las pautas de publicación, la representación del contenido y la optimización de la recuperación. Se entremezclan conceptos de Psicología Cognitiva,Lingüística, Cienciometría, Documentación, Estadística, Clasificación e Informática en sus vertientes
más relacionadas con el tratamiento, organización y caracterización de información textual.

El objetivo final es analizar la influencia que tiene el análisis de
género en la carcterización de los parámetros cualitativos y cuantitativos, y en concreto, de las herramientas que se encargan tradicionalmente de estos estudios, como los indicadores cienciométricos y la clasificación de términos.

Papers by Jorge Morato

Influence of Term Familiarity in Readability of Spanish e-Government Web Information

It is well known that linguistic features of a written text affect its readability, understanding... more It is well known that linguistic features of a written text affect its readability, understanding readability as the ease with which a reader can understand the text. This paper is focused on the analysing of the influence of some linguistic features on the readability of current Spanish e-Government websites. Specifically, the “familiarity” of the terms on web pages, as well as the “frequency” of these terms are studied, among others. Firstly, this research has analysed a corpus extracted from the current information websites of the Spanish eGovernment and its simplified counterparts. Then, using machine learning methods, a supervised model is built on the influence of different term familiarity lists on text readability in the corpus. Different term lists have been tested and it has been concluded that the differences between them have a great impact on their performance. An accuracy of 81% has been achieved with a combination of frequency lists. As a conclusion, term lists and th...

Knowledge management in biomedical libraries: A semantic web approach

by Damaris Fuentes-Lorenzo and Jorge Morato

Information Systems Frontiers, Jan 1, 2009

In recent years, technological advances in highthroughput techniques and efficient data gathering... more In recent years, technological advances in highthroughput techniques and efficient data gathering methods, coupled with a world-wide effort in computational biology, have resulted in an enormous amount of life science data available in repositories devoted to biomedical literature. These repositories lack the ability to attain an effective and accurate search. Using semantic technologies as the key for interoperation enables searching and processing of biomedical literature in a more efficient way. However, emerging semantic applications take for granted specific knowledge that biomedical researchers may not have. This paper presents design principles for easy-to-use biomedical semantic applications by means of ontology-based annotations and faceted search. The proposed approach is backed with a usable prototype that shows the breakthroughs of adding these principles to a biomedical digital library where identifying and searching information are critical aspects for non-semantic Web experts.

Feature Based Automatic Text Summarization Methods: A Comprehensive State-of-the-Art Survey

IEEE Access

With the advent of the World Wide Web, there are numerous online platforms that generate huge amo... more With the advent of the World Wide Web, there are numerous online platforms that generate huge amounts of textual material, including social networks, online blogs, magazines, etc. This textual content contains useful information that can be used to advance humanity. Text summarization has been a significant area of research in natural language processing (NLP). With the expansion of the internet, the amount of data in the world has exploded. Large volumes of data make locating the required and best information time-consuming. It is impractical to manually summarize petabytes of data; hence, computerized text summarization is rising in popularity. This study presents a comprehensive overview of the current status of text summarizing approaches, techniques, standard datasets, assessment criteria, and future research directions. The summarizing approaches are assessed based on several characteristics, including approachbased, document-number-based, Summarization domain-based, document-language-based, output summary nature, etc. This study concludes with a discussion of many obstacles and research opportunities linked to text summarizing research that may be relevant for future researchers in this field.

WordNet applications

Automatic Text Summarization for Hindi Using Real Coded Genetic Algorithm

Applied Sciences

In the present scenario, Automatic Text Summarization (ATS) is in great demand to address the eve... more In the present scenario, Automatic Text Summarization (ATS) is in great demand to address the ever-growing volume of text data available online to discover relevant information faster. In this research, the ATS methodology is proposed for the Hindi language using Real Coded Genetic Algorithm (RCGA) over the health corpus, available in the Kaggle dataset. The methodology comprises five phases: preprocessing, feature extraction, processing, sentence ranking, and summary generation. Rigorous experimentation on varied feature sets is performed where distinguishing features, namely- sentence similarity and named entity features are combined with others for computing the evaluation metrics. The top 14 feature combinations are evaluated through Recall-Oriented Understudy for Gisting Evaluation (ROUGE) measure. RCGA computes appropriate feature weights through strings of features, chromosomes selection, and reproduction operators: Simulating Binary Crossover and Polynomial Mutation. To extr...

Trends in the technological profile of information professionals

New technologies require an upgrade of LIS professionals’ skills. This study analyzes changes in ... more New technologies require an upgrade of LIS professionals’ skills. This study analyzes changes in the field and suggests guidelines to improve LIS curriculum. We have carried out a content analysis of 20 curricula from LIS educational programs to identify terms associated with technological skills. In addition, we identified terms related to new competences from 735 job openings published on generic web sites and 170 on specific web sites. These terms include marketing, management, and content management, mainly related to web applications. The results confirm a positive trend in the demand for technological skills related to LIS. Nevertheless, there is a need to increase awareness about the competences and abilities of LIS professionals, because many relevant job openings are listed in other job categories. Therefore, we have collected a list of key technological skills. In conclusion, it is clear that computer science and the Internet are bringing new opportunities to LIS professio...

Diseño de una herramienta para la Creación Asistida de KOS

&amp;amp;quot;La automatización del proceso de adquisición de conocimiento a partir de docume... more &amp;amp;quot;La automatización del proceso de adquisición de conocimiento a partir de documentos textuales en formato electrónico conlleva múltiples dificultades. Una de esas dificultades es el tratamiento textual en si mismo por la diversidad de formatos o su ausencia. Así una metodología idónea deberá marcar bajo que pautas estos documentos serán tratados. Por otra parte, un procesamiento lingüístico potente es necesario para salvar estas dificultades.  Se ha mostrado una metodología que está demostrando ser eficiente en distintos dominios y aplicaciones.  La automatización completa por el momento no ha resultado factible.  Existen en estudio múltiples aplicaciones a Vigilancia tecnológica y Reutilización de Software.  Según los experimentos desarrollados, la metodología idónea debe estar basada en una clasificación facetada que facilite la reutilización e interoperabilidad de estos sistemas de sistemas de organización del conocimiento.  Todas las experiencias ensayadas indican que las clasificaciones propuestas, tras la aplicación de las herramientas informáticas al análisis de un dominio, deberán ser valoradas y validadas por un experto. Por el momento una automatización totalmente ajena a la intervención humana no parece ser realista. Como futuro desarrollo se deberá resolver los problemas asociadas a la validación por los expertos en el dominio, ya que provoca demoras e inconsistencias en la obtención del dominio. En conclusión, las tareas asignadas a los expertos deberán ser breves y sencillas para que la metodología sea efectiva, o bien ser simplificadas mediante minería de datos.&amp;amp;quot;

Estructuración Y Clasificación Automática De Información: Aplicación a Una Colección De Textos Médicos

Revista Interamericana de Bibliotecología, 2001

Título: Estructuración y clasificación automática de información: aplicación a una colección de t... more

Software Engineering Research

Research Methodologies, Innovations and Philosophies in Software Systems Engineering and Information Systems

Informetric Quality Measures in an Automatic Domain Generation Enviroment

Evaluation of Named Entity Extraction Systems

… in Computing Science, 2009

Abstract. The suitability of the algorithms for recognition and classification of entities (NERC)... more

Using the Shape of Music to Compute the Similarity Between Symbolic Musical Pieces

Málaga (Spain …, 2010

Abstract. We describe a new approach for computing the similarity between symbolic musical pieces... more

Ontologies evaluation for a conceptual retrieval system of metadata schemes: Case study

2013 Sixth International Conference on Contemporary Computing (IC3), 2013

ABSTRACT In this article we perform a qualitative analysis of well-known generic ontologies accor... more ABSTRACT In this article we perform a qualitative analysis of well-known generic ontologies according to their retrieval potential in order to implement a conceptual retrieval system. This retrieval system aims to search metadata schemes. The main problem in the implementation of retrieval system has been finding a reference ontology covering the domain and matching the system&#39;s requirements. We performed an evaluation of ontologies&#39; characteristics for their suitability to represent the semantic of specific metadata scheme. Finally, PROTON has been selected as ontology due to its extensibility, adaptability to the domain, adequacy to the retrieval system and its availability. The principal contribution of this study is the provision of guidelines towards the selection of ontologies to be mapped, based on qualitative analysis and experience.

Audio Music Similarity And Retrieval: Evaluation Power And Stability

In this paper we analyze the reliability of the results in the evaluation of Audio Music Similari... more In this paper we analyze the reliability of the results in the evaluation of Audio Music Similarity and Retrieval systems. We focus on the power and stability of the evaluation, that is, how often a significant difference is found between systems and how often these significant differences are incorrect. We study the effect of using different effectiveness measures with different sets of relevance judgments, for varying number of queries and alternative statistical procedures. Different measures are shown to behave similarly overall, though some are much more sensitive and stable than others. The use of different statistical procedures does improve the reliability of the results, and it allows using as little as half the number of queries currently used in MIREX evaluations while still offering very similar reliability levels. We also conclude that experimenters can be very confident that if a significant difference is found between two systems, the difference is indeed real.

Information Retrieval Systems Adapted to the Biomedical Domain

The terminology used in Biomedicine shows lexical peculiarities that have required the elaboratio... more The terminology used in Biomedicine shows lexical peculiarities that have required the elaboration of terminological resources and information retrieval systems with specific functionalities. The main characteristics are the high rates of synonymy and homonymy, due to phenomena such as the proliferation of polysemic acronyms and their interaction with common language. Information retrieval systems in the biomedical domain use techniques oriented to the treatment of these lexical peculiarities. In this paper we review some of the techniques used in this domain, such as the application of Natural Language Processing (BioNLP), the incorporation of lexical-semantic resources, and the application of Named Entity Recognition (BioNER). Finally, we present the evaluation methods adopted to assess the suitability of these techniques for retrieving biomedical resources.

Diseño de una aplicación móvil de bajo coste para redes de bibliotecas

Ibersid: revista de sistemas de información y documentación, 2020

Se presenta el desarrollo de una aplicación móvil de bajo costo para una red de bibliotecas. Exis... more Se presenta el desarrollo de una aplicación móvil de bajo costo para una red de bibliotecas. Existe una necesidad de aplicaciones que proporcionen servicio a los usuarios de las bibliotecas de acuerdo con los usos actuales, fidelizando a los usuarios y simplificando el acceso recurrente a múltiples sitios web. Se utiliza la Red Valenciana de Lectura Pública como estudio de caso para ilustrar la propuesta. El punto de partida es un proceso analítico relativo a las características de la entidad y los requisitos de la aplicación móvil. Para el desarrollo de la aplicación se comparan diferentes plataformas para la construcción de aplicaciones móviles. A continuación, se evalúa el producto final en relación con la eficiencia y la facilidad de uso. Los resultados indican que la utilización de una aplicación, que integra la información en un único punto, mejora el rendimiento en términos de tiempo de búsqueda y tasa de error. La principal contribución de este trabajo destaca las apps como ...

A study of labour market information needs through employers' seeking behaviour

Inf. Res., 2010

Introduction. The objective of this study is understand the information needs that businesses hav... more Introduction. The objective of this study is understand the information needs that businesses have while seeking Library and Information Science professionals and analyse how they formulate those needs. Method. The analysis is performed by examining the professional skills and capabilities demanded in job offers published. A total of 1,020 job offers collected from a Spanish employment agency Website have been analysed for the period between 2006 and 2008. Analysis. Knowledge representation techniques using thesauri have been used for the automatic content analysis based on natural language processing. Data extracted from the corpora have been analysed statistically. Results. Results of this study indicate a demand for skills related to technological advances and the management of electronic resources as well as to technical aspects associated with the Informatics domain. The knowledge of languages and the possession of an academic title represent essential factors in the job offers...

Posicionamiento de proyectos de software en base al análisis de los grafos de sus relaciones de dependencia

Open source software is becoming more popular worldwide due to the quality of its products. Open ... more Open source software is becoming more popular worldwide due to the quality of its products. Open source repositories are tools to access this kind of software, but when it comes to search any particular component, it is not easy to find what is required quickly. This paper studies the feasibility of using other sorting algorithms, in order to improve the results provided by open source software repositories; for this purpose the use of sorting algorithms based on graphs of relationships between open source software projects is analyzed. The results of four different sorting algorithms have been compared with the opinion of a group of experts in the domain area where the experiment was conducted. The results show that there are slight discrepancies between the ranking provided by the open source repository, sorting algorithms and expert opinion. These results underscore the possibility of including new sorting techniques in open source repositories in order to obtain better results i...

glossariumBITri: Interdisciplinary Elucidation of Concepts, Metaphors, Theories and Problems Concerning INFORMATION - 2nd Edition

by Jose Maria Diaz Nafria, Francisco Salto Alemany, Juan Miguel Aguado, Gordana Dodig-Crnkovic, M. Burgin, Manuel Campos-Havidich, Roberto Gejman, Jorge Morato, Rosa Macarro, and Blanca Bravo

The glossariumBITri, planned as a central activity for the interdisciplinary study of information... more The glossariumBITri, planned as a central activity for the interdisciplinary study of information, developed by BITrum group in cooperation with the University of Santa Elena (Ecuador), essentially aims at serving as a tool for the clarification of concepts, theories and problems concerning information. Intending to embrace the most relevant points of view with respect to information, it is interdisciplinarily developed by a board of experts coming from a wide variety of scientific fields. The glossariumBITri kindly invites the scientific community to make contributions of any kind aimed at clarifying in the field of information studies.

Análisis de relaciones cienciométricas y lingüisticas en un entorno automatizado

Se presenta una visión integradora de las diferentes herramientas que permiten el estudio de las ... more Se presenta una visión integradora de las diferentes herramientas que permiten el estudio de las conexiones entre documentos, las pautas de publicación, la representación del contenido y la optimización de la recuperación. Se entremezclan conceptos de Psicología Cognitiva,Lingüística, Cienciometría, Documentación, Estadística, Clasificación e Informática en sus vertientes
más relacionadas con el tratamiento, organización y caracterización de información textual.

El objetivo final es analizar la influencia que tiene el análisis de
género en la carcterización de los parámetros cualitativos y cuantitativos, y en concreto, de las herramientas que se encargan tradicionalmente de estos estudios, como los indicadores cienciométricos y la clasificación de términos.

Influence of Term Familiarity in Readability of Spanish e-Government Web Information

It is well known that linguistic features of a written text affect its readability, understanding... more It is well known that linguistic features of a written text affect its readability, understanding readability as the ease with which a reader can understand the text. This paper is focused on the analysing of the influence of some linguistic features on the readability of current Spanish e-Government websites. Specifically, the “familiarity” of the terms on web pages, as well as the “frequency” of these terms are studied, among others. Firstly, this research has analysed a corpus extracted from the current information websites of the Spanish eGovernment and its simplified counterparts. Then, using machine learning methods, a supervised model is built on the influence of different term familiarity lists on text readability in the corpus. Different term lists have been tested and it has been concluded that the differences between them have a great impact on their performance. An accuracy of 81% has been achieved with a combination of frequency lists. As a conclusion, term lists and th...

Knowledge management in biomedical libraries: A semantic web approach

by Damaris Fuentes-Lorenzo and Jorge Morato

Information Systems Frontiers, Jan 1, 2009

In recent years, technological advances in highthroughput techniques and efficient data gathering... more In recent years, technological advances in highthroughput techniques and efficient data gathering methods, coupled with a world-wide effort in computational biology, have resulted in an enormous amount of life science data available in repositories devoted to biomedical literature. These repositories lack the ability to attain an effective and accurate search. Using semantic technologies as the key for interoperation enables searching and processing of biomedical literature in a more efficient way. However, emerging semantic applications take for granted specific knowledge that biomedical researchers may not have. This paper presents design principles for easy-to-use biomedical semantic applications by means of ontology-based annotations and faceted search. The proposed approach is backed with a usable prototype that shows the breakthroughs of adding these principles to a biomedical digital library where identifying and searching information are critical aspects for non-semantic Web experts.

Feature Based Automatic Text Summarization Methods: A Comprehensive State-of-the-Art Survey

IEEE Access

With the advent of the World Wide Web, there are numerous online platforms that generate huge amo... more With the advent of the World Wide Web, there are numerous online platforms that generate huge amounts of textual material, including social networks, online blogs, magazines, etc. This textual content contains useful information that can be used to advance humanity. Text summarization has been a significant area of research in natural language processing (NLP). With the expansion of the internet, the amount of data in the world has exploded. Large volumes of data make locating the required and best information time-consuming. It is impractical to manually summarize petabytes of data; hence, computerized text summarization is rising in popularity. This study presents a comprehensive overview of the current status of text summarizing approaches, techniques, standard datasets, assessment criteria, and future research directions. The summarizing approaches are assessed based on several characteristics, including approachbased, document-number-based, Summarization domain-based, document-language-based, output summary nature, etc. This study concludes with a discussion of many obstacles and research opportunities linked to text summarizing research that may be relevant for future researchers in this field.

WordNet applications

Automatic Text Summarization for Hindi Using Real Coded Genetic Algorithm

Applied Sciences

In the present scenario, Automatic Text Summarization (ATS) is in great demand to address the eve... more In the present scenario, Automatic Text Summarization (ATS) is in great demand to address the ever-growing volume of text data available online to discover relevant information faster. In this research, the ATS methodology is proposed for the Hindi language using Real Coded Genetic Algorithm (RCGA) over the health corpus, available in the Kaggle dataset. The methodology comprises five phases: preprocessing, feature extraction, processing, sentence ranking, and summary generation. Rigorous experimentation on varied feature sets is performed where distinguishing features, namely- sentence similarity and named entity features are combined with others for computing the evaluation metrics. The top 14 feature combinations are evaluated through Recall-Oriented Understudy for Gisting Evaluation (ROUGE) measure. RCGA computes appropriate feature weights through strings of features, chromosomes selection, and reproduction operators: Simulating Binary Crossover and Polynomial Mutation. To extr...

Trends in the technological profile of information professionals

New technologies require an upgrade of LIS professionals’ skills. This study analyzes changes in ... more New technologies require an upgrade of LIS professionals’ skills. This study analyzes changes in the field and suggests guidelines to improve LIS curriculum. We have carried out a content analysis of 20 curricula from LIS educational programs to identify terms associated with technological skills. In addition, we identified terms related to new competences from 735 job openings published on generic web sites and 170 on specific web sites. These terms include marketing, management, and content management, mainly related to web applications. The results confirm a positive trend in the demand for technological skills related to LIS. Nevertheless, there is a need to increase awareness about the competences and abilities of LIS professionals, because many relevant job openings are listed in other job categories. Therefore, we have collected a list of key technological skills. In conclusion, it is clear that computer science and the Internet are bringing new opportunities to LIS professio...

Diseño de una herramienta para la Creación Asistida de KOS

&amp;amp;quot;La automatización del proceso de adquisición de conocimiento a partir de docume... more &amp;amp;quot;La automatización del proceso de adquisición de conocimiento a partir de documentos textuales en formato electrónico conlleva múltiples dificultades. Una de esas dificultades es el tratamiento textual en si mismo por la diversidad de formatos o su ausencia. Así una metodología idónea deberá marcar bajo que pautas estos documentos serán tratados. Por otra parte, un procesamiento lingüístico potente es necesario para salvar estas dificultades.  Se ha mostrado una metodología que está demostrando ser eficiente en distintos dominios y aplicaciones.  La automatización completa por el momento no ha resultado factible.  Existen en estudio múltiples aplicaciones a Vigilancia tecnológica y Reutilización de Software.  Según los experimentos desarrollados, la metodología idónea debe estar basada en una clasificación facetada que facilite la reutilización e interoperabilidad de estos sistemas de sistemas de organización del conocimiento.  Todas las experiencias ensayadas indican que las clasificaciones propuestas, tras la aplicación de las herramientas informáticas al análisis de un dominio, deberán ser valoradas y validadas por un experto. Por el momento una automatización totalmente ajena a la intervención humana no parece ser realista. Como futuro desarrollo se deberá resolver los problemas asociadas a la validación por los expertos en el dominio, ya que provoca demoras e inconsistencias en la obtención del dominio. En conclusión, las tareas asignadas a los expertos deberán ser breves y sencillas para que la metodología sea efectiva, o bien ser simplificadas mediante minería de datos.&amp;amp;quot;

Estructuración Y Clasificación Automática De Información: Aplicación a Una Colección De Textos Médicos

Revista Interamericana de Bibliotecología, 2001

Título: Estructuración y clasificación automática de información: aplicación a una colección de t... more

Software Engineering Research

Research Methodologies, Innovations and Philosophies in Software Systems Engineering and Information Systems

Informetric Quality Measures in an Automatic Domain Generation Enviroment

Evaluation of Named Entity Extraction Systems

… in Computing Science, 2009

Abstract. The suitability of the algorithms for recognition and classification of entities (NERC)... more

Using the Shape of Music to Compute the Similarity Between Symbolic Musical Pieces

Málaga (Spain …, 2010

Abstract. We describe a new approach for computing the similarity between symbolic musical pieces... more

Ontologies evaluation for a conceptual retrieval system of metadata schemes: Case study

2013 Sixth International Conference on Contemporary Computing (IC3), 2013

ABSTRACT In this article we perform a qualitative analysis of well-known generic ontologies accor... more ABSTRACT In this article we perform a qualitative analysis of well-known generic ontologies according to their retrieval potential in order to implement a conceptual retrieval system. This retrieval system aims to search metadata schemes. The main problem in the implementation of retrieval system has been finding a reference ontology covering the domain and matching the system&#39;s requirements. We performed an evaluation of ontologies&#39; characteristics for their suitability to represent the semantic of specific metadata scheme. Finally, PROTON has been selected as ontology due to its extensibility, adaptability to the domain, adequacy to the retrieval system and its availability. The principal contribution of this study is the provision of guidelines towards the selection of ontologies to be mapped, based on qualitative analysis and experience.

Audio Music Similarity And Retrieval: Evaluation Power And Stability

In this paper we analyze the reliability of the results in the evaluation of Audio Music Similari... more In this paper we analyze the reliability of the results in the evaluation of Audio Music Similarity and Retrieval systems. We focus on the power and stability of the evaluation, that is, how often a significant difference is found between systems and how often these significant differences are incorrect. We study the effect of using different effectiveness measures with different sets of relevance judgments, for varying number of queries and alternative statistical procedures. Different measures are shown to behave similarly overall, though some are much more sensitive and stable than others. The use of different statistical procedures does improve the reliability of the results, and it allows using as little as half the number of queries currently used in MIREX evaluations while still offering very similar reliability levels. We also conclude that experimenters can be very confident that if a significant difference is found between two systems, the difference is indeed real.

Information Retrieval Systems Adapted to the Biomedical Domain

The terminology used in Biomedicine shows lexical peculiarities that have required the elaboratio... more The terminology used in Biomedicine shows lexical peculiarities that have required the elaboration of terminological resources and information retrieval systems with specific functionalities. The main characteristics are the high rates of synonymy and homonymy, due to phenomena such as the proliferation of polysemic acronyms and their interaction with common language. Information retrieval systems in the biomedical domain use techniques oriented to the treatment of these lexical peculiarities. In this paper we review some of the techniques used in this domain, such as the application of Natural Language Processing (BioNLP), the incorporation of lexical-semantic resources, and the application of Named Entity Recognition (BioNER). Finally, we present the evaluation methods adopted to assess the suitability of these techniques for retrieving biomedical resources.

Diseño de una aplicación móvil de bajo coste para redes de bibliotecas

Ibersid: revista de sistemas de información y documentación, 2020

Se presenta el desarrollo de una aplicación móvil de bajo costo para una red de bibliotecas. Exis... more Se presenta el desarrollo de una aplicación móvil de bajo costo para una red de bibliotecas. Existe una necesidad de aplicaciones que proporcionen servicio a los usuarios de las bibliotecas de acuerdo con los usos actuales, fidelizando a los usuarios y simplificando el acceso recurrente a múltiples sitios web. Se utiliza la Red Valenciana de Lectura Pública como estudio de caso para ilustrar la propuesta. El punto de partida es un proceso analítico relativo a las características de la entidad y los requisitos de la aplicación móvil. Para el desarrollo de la aplicación se comparan diferentes plataformas para la construcción de aplicaciones móviles. A continuación, se evalúa el producto final en relación con la eficiencia y la facilidad de uso. Los resultados indican que la utilización de una aplicación, que integra la información en un único punto, mejora el rendimiento en términos de tiempo de búsqueda y tasa de error. La principal contribución de este trabajo destaca las apps como ...

A study of labour market information needs through employers' seeking behaviour

Inf. Res., 2010

Introduction. The objective of this study is understand the information needs that businesses hav... more Introduction. The objective of this study is understand the information needs that businesses have while seeking Library and Information Science professionals and analyse how they formulate those needs. Method. The analysis is performed by examining the professional skills and capabilities demanded in job offers published. A total of 1,020 job offers collected from a Spanish employment agency Website have been analysed for the period between 2006 and 2008. Analysis. Knowledge representation techniques using thesauri have been used for the automatic content analysis based on natural language processing. Data extracted from the corpora have been analysed statistically. Results. Results of this study indicate a demand for skills related to technological advances and the management of electronic resources as well as to technical aspects associated with the Informatics domain. The knowledge of languages and the possession of an academic title represent essential factors in the job offers...

Posicionamiento de proyectos de software en base al análisis de los grafos de sus relaciones de dependencia

Open source software is becoming more popular worldwide due to the quality of its products. Open ... more Open source software is becoming more popular worldwide due to the quality of its products. Open source repositories are tools to access this kind of software, but when it comes to search any particular component, it is not easy to find what is required quickly. This paper studies the feasibility of using other sorting algorithms, in order to improve the results provided by open source software repositories; for this purpose the use of sorting algorithms based on graphs of relationships between open source software projects is analyzed. The results of four different sorting algorithms have been compared with the opinion of a group of experts in the domain area where the experiment was conducted. The results show that there are slight discrepancies between the ranking provided by the open source repository, sorting algorithms and expert opinion. These results underscore the possibility of including new sorting techniques in open source repositories in order to obtain better results i...

Optical Character Recognition for Hindi Language Using a Neural-network Approach

Journal of Information Processing Systems, 2013

Hindi is the most widely spoken language in India, with more than 300 million speakers. As there ... more Hindi is the most widely spoken language in India, with more than 300 million speakers. As there is no separation between the characters of texts written in Hindi as there is in English, the Optical Character Recognition (OCR) systems developed for the Hindi language carry a very poor recognition rate. In this paper we propose an OCR for printed Hindi text in Devanagari script, using Artificial Neural Network (ANN), which improves its efficiency. One of the major reasons for the poor recognition rate is error in character segmentation. The presence of touching characters in the scanned documents further complicates the segmentation process, creating a major problem when designing an effective character segmentation technique. Preprocessing, character segmentation, feature extraction, and finally, classification and recognition are the major steps which are followed by a general OCR. The preprocessing tasks considered in the paper are conversion of gray scaled images to binary images, image rectification, and segmentation of the document´s textual contents into paragraphs, lines, words, and then at the level of basic symbols. The basic symbols, obtained as the fundamental unit from the segmentation process, are recognized by the neural classifier. In this work, three feature extraction techniques-: histogram of projection based on mean distance, histogram of projection based on pixel value, and vertical zero crossing, have been used to improve the rate of recognition. These feature extraction techniques are powerful enough to extract features of even distorted characters/symbols. For development of the neural classifier, a back-propagation neural network with two hidden layers is used. The classifier is trained and tested for printed Hindi texts. A performance of approximately 90% correct recognition rate is achieved.

Glossary of concepts, metaphors, theories and problems concerning INFORMATION

ABSTRACT