Graphic summary
  • Show / hide key
  • Information


Scientific and technological production
  •  

1 to 50 of 52 results
  • FAUST. Open source release of the final Asiya Suite

     Gonzalez Bermudez, Meritxell; Mascarell, Laura; Màrquez Villodre, Lluís
    Date: 2013-02-18
    Report

     Share Reference managers Reference managers Open in new window

  • Access to the full text
    The use of domain ontologies for improving the adaptability and collaborative ability of a web dialogue system  Open access

     Gonzalez Bermudez, Meritxell; Gatius Vila, Marta
    International Journal of Computer Information Systems and Industrial Management Applications
    Date of publication: 2013
    Journal article

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    Dialogue systems can be used for guiding the users accessing web services, enhancing the web usability. However, they are expensive to develop and difficult to adapt to different types of web services. The knowledge model of a web service can be seen as the basis to define the semantics of the information to be exchanged among the components of a dialogue system. This approach facilitates the integration of the different types of knowledge involved in human-machine communication and provides a unified framework easier to apply to new web services. Furthermore, the representation of the web service knowledge according to an ontology can enhance the reasoning capabilities of the underlying system. This article describes the use of domain ontologies in a mixed-initiative web dialogue system for improving both its adaptability and its collaborative ability.

  • MOLTO. Patent MT and retrieval. Final report.

     Mateva, Maria; Gonzalez Bermudez, Meritxell; Enache, Ramona; España Bonet, Cristina; Màrquez Villodre, Lluís; Popov, Borislav; Ranta, Aarne
    Date: 2013-03-01
    Report

     Share Reference managers Reference managers Open in new window

  • MOLTO. Final report: statistical and robust MT

     España Bonet, Cristina; Enache, Ramona; Angelov, Krasimir; Virk, Shafqat; Galgoczy, Érzsebet; Gonzalez Bermudez, Meritxell; Ranta, Aarne; Màrquez Villodre, Lluís
    Date: 2013-04-08
    Report

     Share Reference managers Reference managers Open in new window

  • Access to the full text
    tSEARCH: flexible and fast search over automatic translations for improved quality/error analysis  Open access

     Gonzalez Bermudez, Meritxell; Mascarell, Laura; Màrquez Villodre, Lluís
    Annual Meeting of the Association for Computational Linguistics
    Presentation's date: 2013-08-06
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    This work presents tSEARCH, a web-based application that provides mechanisms for doing complex searches over a collection of translation cases evaluated with a large set of diverse measures. tSEARCH uses the evaluation results obtained with the ASIYA toolkit for MT evaluation and it is connected to its on-line GUI, which makes possible a graphical visualization and interactive access to the evaluation results. The search engine offers a flexible query language allowing to find translation examples matching a combination of numerical and structural features associated to the calculation of the quality metrics. Its database design permits a fast response time for all queries supported on realistic-size test beds. In summary, tSEARCH, used with ASIYA, offers developers of MT systems and evaluation metrics a powerful tool for helping translation and error analysis.

    This work presents tSEARCH, a web-based application that provides mechanisms for doing complex searches over a collection of translation cases evaluated with a large set of diverse measures. tSEARCH uses the evaluation results obtained with the ASIYA toolkit for MT evaluation and it is connected to its on-line GUI, which makes possible a graphical visualization and interactive access to the evaluation results. The search engine offers a flexible query language allowing to find translation examples matching a combination of numerical and structural features associated to the calculation of the quality metrics. Its database design permits a fast response time for all queries supported on realistic-size test beds. In summary, tSEARCH, used with ASIYA, offers developers of MT systems and evaluation metrics a powerful tool for helping translation and error analysis.

  • Access to the full text
    MT techniques in a retrieval system of semantically enriched patents  Open access

     Gonzalez Bermudez, Meritxell; Mateva, Maria; Enache, Ramona; España Bonet, Cristina; Màrquez Villodre, Lluís; Popov, Borislav; Ranta, Aarne
    Machine Translation Summit
    Presentation's date: 2013-09-04
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    This paper focuses on how automatic translation techniques integrated in a patent retrieval system increase its capabilities and make possible extended features and functionalities. We describe 1) a novel methodology for natural language to SPARQL translation based on a grammar¿ ontology interoperability automation and a query grammar for the patents domain; 2) a devised strategy for statisticalbased translation of patents that allows to transfer semantic annotations to the target language; 3) a built-in knowledge representation infrastructure that uses multilingual semantic annotations; and 4) an online application that offers a multilingual search interface over structural knowledge databases (domain ontologies) and multilingual documents (biomedical patents) that have been automatically translated.

    This paper focuses on how automatic translation techniques integrated in a patent retrieval system increase its capabilities and make possible extended features and functionalities. We describe 1) a novel methodology for natural language to SPARQL translation based on a grammar– ontology interoperability automation and a query grammar for the patents domain; 2) a devised strategy for statisticalbased translation of patents that allows to transfer semantic annotations to the target language; 3) a built-in knowledge representation infrastructure that uses multilingual semantic annotations; and 4) an online application that offers a multilingual search interface over structural knowledge databases (domain ontologies) and multilingual documents (biomedical patents) that have been automatically translated.

  • The TALP-UPC approach to system selection: ASIYA features and pairwise classification using random forests

     Formiga Fanals, Lluis; Gonzalez Bermudez, Meritxell; Barron Cedeño, Luis Alberto; Rodríguez Fonollosa, José Adrián; Màrquez Villodre, Lluís
    Workshop on Statistical Machine Translation
    Presentation's date: 2013-08-08
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    This paper describes the TALP-UPC participation in the WMT¿13 Shared Task on Quality Estimation (QE). Our participation is reduced to task 1.2 on System Selection. We used a broad set of features (86 for German-to-English and 97 for English-to-Spanish) ranging from standard QE features to features based on pseudo-references and semantic similarity. We approached system selection by means of pairwise ranking decisions. For that, we learned Random Forest classifiers especially tailored for the problem. Evaluation at development time showed considerably good results in a cross-validation experiment, with Kendall¿s values around 0.30. The results on the test set dropped significantly, raising different discussions to be taken into account.

    This paper describes the TALP-UPC participation in the WMT’13 Shared Task on Quality Estimation (QE). Our participation is reduced to task 1.2 on System Selection. We used a broad set of features (86 for German-to-English and 97 for English-to-Spanish) ranging from standard QE features to features based on pseudo-references and semantic similarity. We approached system selection by means of pairwise ranking decisions. For that, we learned Random Forest classifiers especially tailored for the problem. Evaluation at development time showed considerably good results in a cross-validation experiment, with Kendall’s values around 0.30. The results on the test set dropped significantly, raising different discussions to be taken into account.

  • MOLTO. Patent MT and retrieval prototype

     Gonzalez Bermudez, Meritxell; Chechev, Milen; Damova, Mariana; Enache, Ramona; España Bonet, Cristina; Màrquez Villodre, Lluís; Mateva, Maria; Ranta, Aarne; Tolosi, Laura
    Date: 2012-09-01
    Report

     Share Reference managers Reference managers Open in new window

  • FAUST. Asiya user manual

     Giménez Linares, Jesús; Gonzalez Bermudez, Meritxell
    Date: 2012-09-26
    Report

     Share Reference managers Reference managers Open in new window

  • Access to the full text
    A graphical interface for MT evaluation and error analysis  Open access

     Gonzalez Bermudez, Meritxell; Giménez Lucas, Judit; Màrquez Villodre, Lluís
    Annual Meeting of the Association for Computational Linguistics
    Presentation's date: 2012-07-10
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    Error analysis in machine translation is a necessary step in order to investigate the strengths and weaknesses of the MT systems under development and allow fair comparisons among them. This work presents an application that shows how a set of heterogeneous automatic metrics can be used to evaluate a test bed of automatic translations. To do so, we have set up an online graphical interface for the ASIYA toolkit, a rich repository of evaluation measures working at different linguistic levels. The current implementation of the interface shows constituency and dependency trees as well as shallow syntactic and semantic annotations, and word alignments. The intelligent visualization of the linguistic structures used by the metrics, as well as a set of navigational functionalities, may lead towards advanced methods for automatic error analysis.

  • The patents retrieval prototype in the MOLTO project

     Chechev, Milen; Gonzalez Bermudez, Meritxell; Màrquez Villodre, Lluís; España Bonet, Cristina
    International World Wide Web Conference
    Presentation's date: 2012-04-16
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    This paper describes the patents retrieval prototype developed within the MOLTO project. The prototype aims to provide a multilingual natural language interface for querying the content of patent documents. The developed system is focused on the biomedical and pharmaceutical domain and includes the translation of the patent claims and abstracts into English, French and German. Aiming at the best retrieval results of the patent information and text content, patent documents are preprocessed and semantically annotated. Then, the annotations are stored and indexed in an OWLIM semantic repository, which contains a patent specific ontology and others from different domains. The prototype, accessible online at http://molto-patents.ontotext.com, presents a multilingual natural language interface to query the retrieval system. In MOLTO, the multilingualism of the queries is addressed by means of the GF Tool, which provides an easy way to build and maintain controlled language grammars for interlingual translation in limited domains. The abstract representation obtained from the GF is used to retrieve both the matched RDF instances and the list of patents semantically related to the user's search criteria. The online interface allows to browse the retrieved patents and shows on the text the semantic annotations that explain the reason why any particular patent has matched the user's criteria.

    This paper describes the patents retrieval prototype developed within the MOLTO project. The prototype aims to provide a multilingual natural language interface for querying the content of patent documents. The developed system is focused on the biomedical and pharmaceutical domain and includes the translation of the patent claims and abstracts into English, French and German. Aiming at the best retrieval results of the patent information and text content, patent documents are preprocessed and semantically annotated. Then, the annotations are stored and indexed in an OWLIM semantic repository, which contains a patent speci c ontology and others from di erent domains. The prototype, accessible online at http://molto-patents. ontotext.com, presents a multilingual natural language interface to query the retrieval system. In MOLTO, the multilingualism of the queries is addressed by means of the GF Tool, which provides an easy way to build and maintain controlled language grammars for interlingual translation in limited domains. The abstract representation obtained from the GF is used to retrieve both the matched RDF instances and the list of patents semantically related to the user's search criteria. The online interface allows to browse the retrieved patents and shows on the text the semantic annotations that explain the reason why any particular patent has matched the user's criteria.

  • Access to the full text
    The UPC submission to the WMT 2012 shared task on quality estimation  Open access

     Pighin, Daniele; Gonzalez Bermudez, Meritxell; Màrquez Villodre, Lluís
    Workshop on Statistical Machine Translation
    Presentation's date: 2012-06-07
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    In this paper, we describe the UPC system that participated in the WMT 2012 shared task on Quality Estimation for Machine Translation. Based on the empirical evidence that fluencyrelated features have a very high correlation with post-editing effort, we present a set of features for the assessment of quality estimation for machine translation designed around different kinds of n-gram language models, plus another set of features that model the quality of dependency parses automatically projected from source sentences to translations. We document the results obtained on the shared task dataset, obtained by combining the features that we designed with the baseline features provided by the task organizers.

  • Aprendizaje y asistencia virtual en red. La prueba Piloto.

     Fuentes Fort, Maria; Gonzalez Bermudez, Meritxell; Guardiola Garcia, Marta; Jofre Roca, Luis; Romeu Robert, Jordi; Vallverdu Bayes, Francisco
    Date: 2011-07-29
    Report

     Share Reference managers Reference managers Open in new window

  • Access to the full text
    Hacia la interacción en lenguaje natural  Open access

     Fuentes Fort, Maria; Gonzalez Bermudez, Meritxell
    CEUR Workshop proceedings
    Date of publication: 2011-02-06
    Journal article

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    En éste documento se presenta la investigación que está siendo llevada a cabo en el Grupo de Procesamiento de Lenguaje Natural (GPLN) de la Universidad Politécnica de Cataluña (UPC). En concreto, hemos articulado la presentación de las diferentes líneas de trabajo tomando como referencia su aplicación en un asistente virtual. Creemos que su uso y implantación irá en aumento en los próximos diez años, de ahí la importancia del estado de las tecnologías del lenguaje natural y, aún mas, de los nuevos retos que este tipo de aplicaciones nos plantean.

  • Access to the full text
    ALICE: Acquisition of Language through an Interactive Comprehension Environment  Open access

     Fuentes Fort, Maria; Gonzalez Bermudez, Meritxell
    Procesamiento del lenguaje natural
    Date of publication: 2011-09-05
    Journal article

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    Integration of several state-of-the-art technologies related to spoken language and natural language processing used in Intelligent Computer Assisted Language Learning (ICALL) systems. We envision to show that the technology has a level of maturity that suggests that the time may be right to use it at high school. // Integración de tecnologías del estado del arte en procesamiento del habla y procesamiento del lenguaje natural aplicadas a los asistentes inteligentes para el aprendizaje de lenguas. El objetivo es mostrar que el nivel de madurez de la tecnología permite que sea aplicada al aprendizaje de segundas lenguas en secundaria.

  • MOLTO. Description of the nal collection of corpora

     España Bonet, Cristina; Gonzalez Bermudez, Meritxell; Màrquez Villodre, Lluís
    Date: 2011-09-12
    Report

     Share Reference managers Reference managers Open in new window

  • Access to the full text
    Aprendizaje y asistencia virtual en red  Open access

     Fuentes Fort, Maria; Gonzalez Bermudez, Meritxell; Guardiola Garcia, Marta; Jofre Roca, Luis; Romeu Robert, Jordi; Vallverdu Bayes, Francisco
    Date: 2011-01-20
    Report

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    Favorecer el uso de las Tecnologías de Información y la Comunicación (TIC) en entornos educativos puede abarcar varios aspectos del proceso de aprendizaje. La incorporación de TICs en las aulas contribuye, por un lado a reducir la brecha digital tanto de profesores como alumnos y por el otro, debiera ayudar a mejorar la metodología educativa. Sin duda las TICs pueden ser de gran ayuda para llegar a alcanzar los objetivos pedagógicos. En concreto, este estudio tenía por objetivo analizar la manera de incorporar tecnologías de la voz y el procesamiento del lenguaje natural para mejorar el proceso de aprendizaje de la lengua. Para identificar cuales son las características de éste proceso, que aspectos se verán modificados con la incorporación de estas tecnologías y como afectaran las modificaciones a cada aspecto del proceso, en Diciembre de 2010 se organizó una jornada que reunió a distintos sectores sociales directamente involucrados con el ámbito a tratar. Como resultado de ésta jornada, en Abril de 2011, se llevará a cabo una prueba piloto en que se incorporará las tecnologías propuestas en el aprendizaje de inglés y ya se ha empezado a definir un proyecto a medio plazo para buscar financiamiento a nivel estatal o europeo.

  • MOLTO. Patent MT and retrieval prototype beta

     Chechev, Milen; Enache, Ramona; España Bonet, Cristina; Gonzalez Bermudez, Meritxell; Màrquez Villodre, Lluís; Popov, Borislav; Ranta, Aarne
    Date: 2011-12-01
    Report

     Share Reference managers Reference managers Open in new window

  • Access to the full text
    Aprendizaje y asistencia virtual en red /Aprenentatge i assistència virtual en xarxa  Open access

     Jofre Roca, Luis; Romeu Robert, Jordi; Vallverdu Bayes, Francisco; Fuentes Fort, Maria; Guardiola Garcia, Marta; Gonzalez Bermudez, Meritxell
    Date of publication: 2011-01
    Book

    Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

  • Access to the full text
    English language learning activity using spoken language and intelligent computer-assisted technologies  Open access

     Fuentes Fort, Maria; Gonzalez Bermudez, Meritxell
    Speech and Language Technology in Education
    Presentation's date: 2011-09-24
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    This paper presents work in progress on language technologies applied to secondary school education. The application presented integrates several state-of-the-art technologies related to spoken language and intelligent computer-assisted language learning. We envision to show that the technology has reached a level of maturity that suggests that the time may be right to use it to second language learning. To achieve this objective, an activity was designed to be tested at several Spanish high schools. The aim was to carry out a proof of concept in real conditions and to obtain feedback from the students through a questionnaire as well as from the teachers by means of an interview. The activity was designed with the collaboration of some of the teachers at the secondary schools.

  • Using domain knowledge for fostering the collaborative ability of a web dialogue system

     Gatius Vila, Marta; Gonzalez Bermudez, Meritxell
    International Conference on Next Generation Web Services Practices
    Presentation's date: 2011-10-20
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Access to the full text
    Patent translation within the MOLTO project  Open access

     España Bonet, Cristina; Enache, Ramona; Slaski, Adam; Ranta, Aarne; Màrquez Villodre, Lluís; Gonzalez Bermudez, Meritxell
    Workshop on Patent Translation
    Presentation's date: 2011-09-23
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    MOLTO is an FP7 European project whose goal is to translate texts between multiple languages in real time with high quality. Patents translation is a case of study where research is focused on simultaneously obtaining a large coverage without loosing quality in the translation. This is achieved by hybridising between a grammar-based multilingual translation system, GF, and a specialised statistical machine translation system. Moreover, both individual systems by themselves already represent a step forward in the translation of patents in the biomedical domain, for which the systems have been trained.

  • Feedback Analysis for User adaptive Statistical Translation

     Màrquez Villodre, Lluís; Formiga Fanals, Lluis; Mariño Acebal, Jose Bernardo; Gonzalez Bermudez, Meritxell; Rodríguez Fonollosa, José Adrián; Monte Moreno, Enrique; Barron Cedeño, Luis Alberto
    Participation in a competitive project

     Share

  • TRADUCCION AUTOMATICA HIBRIDA Y EVALUACION AVANZADA (UPC)

     Castell Ariño, Nuria; Farwell, David Loring; Gimenez Linares, Jesús Ángel; Ferrer Cancho, Ramon; Martin Escofet, Carme; Daude Ventura, Jorge; Abad Soriano, Maria Teresa; Gonzalez Bermudez, Meritxell; Màrquez Villodre, Lluís
    Participation in a competitive project

     Share

  • Multilingual On-Line Translation

     Rodriguez Hontoria, Horacio; Gonzalez Bermudez, Meritxell; España Bonet, Cristina; Farwell, David Loring; Carreras Perez, Xavier; Xambó Descamps, Sebastian; Màrquez Villodre, Lluís; Padró Cirera, Lluís; Saludes Closa, Jordi
    Participation in a competitive project

     Share

  • Combining user intention and error modeling for statistical dialog simulators

     Quarteroni, Silvia; Gonzalez Bermudez, Meritxell; Riccardi, Giuseppe; Varges, Sebastian
    Annual Conference of the International Speech Communication Association
    Presentation's date: 2010-09-30
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Statistical user simulation is an efficient and effective way to train and evaluate the performance of a (spoken) dialog system. In this paper, we design and evaluate a modular data-driven dialog simulator where we decouple the “intentional” component of the User Simulator from the Error Simulator representing different types of ASR/SLU noisy channel distortion. While the former is composed by a Dialog Act Model, a Concept Model and a User Model, the latter is centered around an Error Model. We test different Dialog Act Models and Error Models against a baseline dialog manager and compare results with real dialogs obtained using the same dialog manager. On the grounds of dialog act, task and concept accuracy, our results show that 1) datadriven Dialog Act Models achieve good accuracy with respect to real user behavior and 2) data-driven Error Models make task completion times and rates closer to real data.

  • DIGUI: A Flexible Dialogue System for Guiding the User Interaction to Access Web Services

     Gonzalez Bermudez, Meritxell
    Defense's date: 2010-10-22
    Facultat d'Informàtica de Barcelona (UPC)
    Theses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Access to the full text
    The structure and management of tasks in a dialogue system for accessing web services  Open access

     Gonzalez Bermudez, Meritxell; Gatius Vila, Marta
    Congreso de la Sociedad Española para el Procesamiento del Lenguaje Natural
    Presentation's date: 2010-09-09
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    Los sistemas de diálogo se pueden ver como una interfaz de usuario para acceder a otras aplicaciones. No sólo tienen que tratar con los requerimientos de los usuarios, sino también con los propios de las aplicaciones. Este trabajo se centra en cómo representar y gestionar las tareas para dos tipos de servicios web: transaccionales y búsqueda de información. Los servicios transaccionales suelen ser simples de gestionar, excepto cuando el usuario desconoce el signi cado de los parámetros que el sistema le pide. Los sistemas de búsqueda, en cambio, necesitan estrategias mucho más complejas para acceder a las aplicaciones y mostrar los resultados. De ahí la necesidad de sistemas que guíen al usuario para que pueda acceder de manera fácil a la información. En nuestra propuesta, las especi caciones de las tareas se utilizan para determinar cuándo y cómo obtener más información del usuario, y cómo presentar los resultado de forma clara. // Dialog systems can be seen as user interfaces to access other applications. They have to address the user needs, as well as the requirements of the applications. This work is concerned with the representation and the management of the application tasks. We have studied two types of web services: form- lling and information-seeking. We claim that dialogue systems may not intend to use the same strategies for all types of applications. Form- lling applications do not need assistants, but explanations about the meaning of the elds. Information-seeking engines need complex strategies to access and display results, and hence assistants may guide the user to give the query constraints. In our proposal, the task models we describe are used to determine how to acquire more reliable constraints from the user and how to adapt them in order to obtain more suitable results; as well as the most appropriate presentation of results.

    Postprint (author’s final draft)

  • Guiding the user when searching information on the web

     Gatius Vila, Marta; Gonzalez Bermudez, Meritxell
    Workshop on the Semantics and Pragmatics of Dialogue
    Presentation's date: 2010-06-18
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    This paper describes how we approach the problem of guiding the user when accessing informational web services. We developed a mixed-initiative dialogue system that provides access to web services in several languages. In order to facilitate the adaptation of the system to new informational web services dialogue and task management were separated and general descriptions of the several tasks involved in the communication process were incorporated.

  • Cooperative user models in statistical dialog simulators

     Gonzalez Bermudez, Meritxell; Quarteroni, Silvia; Riccardi, Giuseppe; Varges, Sebastian
    Annual Meeting of the Special Interest Group on Discourse and Dialogue
    Presentation's date: 2010-09-25
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Statistical user simulation is a promising methodology to train and evaluate the performance of (spoken) dialog systems. We work with a modular architecture for data-driven simulation where the "intentional" component of user simulation includes a User Model representing userspecific features. We train a dialog simulator that combines traits of human behavior such as cooperativeness and context with domain-related aspects via the Expectation-Maximization algorithm. We show that cooperativeness provides a finer representation of the dialog context which directly affects task completion rate.

  • Access to the full text
    Un sistema de diálogo flexible para facilitar el uso de la web  Open access

     Gatius Vila, Marta; Gonzalez Bermudez, Meritxell
    Novática: revista de la Asociación de Técnicos de Informática
    Date of publication: 2009
    Journal article

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    En este trabajo presentamos un sistema de diálogo para facilitar al usuario el acceso a diversos contenidos en la web. El prototipo desarrollado permite conversaciones de cierta complejidad, en la que tanto el sistema como el usuario puede tomar la iniciativa. Además, el diseño del sistema facilita su adaptación a diferentes contenidos web y usuarios (diferentes lenguas y diferentes habilidades). El trabajo describe también cómo se ha evaluado el prototipo y los resultados obtenidos.

    Article publicat anteriorment a: Gatius, Marta; González, Meritxell. "Un sistema de diálogo flexible para facilitar el uso de la web". Novática, 2009,año XXXV, núm. 202, noviembre-diciembre, p.56-60.

    Postprint (author’s final draft)

  • A flexible dialogue system for enhancing web usability

     Gatius Vila, Marta; Gonzalez Bermudez, Meritxell
    International World Wide Web Conference
    Presentation's date: 2009
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    In this paper, we study how the performance and usability of web dialogue systems could be enhanced by using an appropriate representation of the different types of knowledge involved in communication: general dialogue mechanisms, specific domainrestricted linguistic and conceptual knowledge and information on how well the communication process is doing. We describe the experiments carried out to analyze how to improve this knowledge representation in the web dialogue system we developed.

  • Natural language processing and dialogue management development

     Gatius Vila, Marta; Gonzalez Bermudez, Meritxell; Comelles, E; Lesmo, L
    Date: 2007-04
    Report

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • An information state-based dialogue manager for making voice web smarter

     Gatius Vila, Marta; Gonzalez Bermudez, Meritxell; Comelles Pujadas, Elisabet
    16th international conference on World Wide Web
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • A multilingual dialogue system for accessing the web

     Gatius Vila, Marta; Gonzalez Bermudez, Meritxell; Comelles Pujadas, Elisabet
    International Conference on Web Information Systems and Technologies
    Presentation's date: 2007
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Discourse management in voice systems for accessing web services

     Gatius Vila, Marta; Gonzalez Bermudez, Meritxell
    Workshop on Semantic and Pragmatic of Dialogue
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • D4.1 HOPS architecture specificacitions

     Vidal Pla, Miguel; Hernández, P; López, A; Sánchez, J; Militelo, S; Barbera, M; Gatius Vila, Marta; Gonzalez Bermudez, Meritxell; Comelles, E; Lesmo, L; Noria, X; Salla, R; Morena, De la C; Fernández, J A; [Et, Al ]
    Date: 2006-06
    Report

     Share Reference managers Reference managers Open in new window

  • Using application-specific ontologies to improve performance in a bottom-up parser

     Gatius Vila, Marta; Gonzalez Bermudez, Meritxell
    11 Conference on the European Chapter of the Association of Computational Linguistics. Workshop on Knowledge and Reasoning for Language Processing
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • FreeLing 1.3: Syntactic and Semantic Services in an Open-Source NLP Library

     Atserias Batalla, Jordi; Casas Fernandez, Bernardino; Comelles Pujadas, Elisabet; Gonzalez Bermudez, Meritxell; Padró Cirera, Lluís; Padro Cirera, Montserrat
    International Conference on Language Resources and Evaluation
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Integrating semantic web and language technologies to improve the online public administrations services

     Gatius Vila, Marta; Gonzalez Bermudez, Meritxell; Militello, S; Hernández, P
    15th International World Wide Web Confernce
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • D3.2. Natural language processing technologies

     Gatius Vila, Marta; Gonzalez Bermudez, Meritxell; Lesmo, L; Torasso, P
    Date: 2005-01
    Report

     Share Reference managers Reference managers Open in new window

  • Un sistema de diálogo multilingüe dirigido por la semántica

     Gatius Vila, Marta; Gonzalez Bermudez, Meritxell
    Procesamiento del lenguaje natural
    Date of publication: 2005-03
    Journal article

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • The project HOPS: enabling an intelligent natural language based hub for the deployment of advanced semantically enriched multi-channel mass-scale online public services

     Gatius Vila, Marta; Gonzalez Bermudez, Meritxell
    Procesamiento del lenguaje natural
    Date of publication: 2005-09
    Journal article

     Share Reference managers Reference managers Open in new window

  • Un sistema de diálogo multicanal para acceder a la información y servicios de las administraciones públicas

     Gonzalez Bermudez, Meritxell; Gatius Vila, Marta
    Procesamiento del lenguaje natural
    Date of publication: 2005-09
    Journal article

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Obtaining linguistic resources for dialogue systems from application specifications and domain ontologies

     Gatius Vila, Marta; Gonzalez Bermudez, Meritxell
    10th International Conference SPEECH and COMPUTER
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Using ontologies for improving the communication process in a dialogue system

     Gatius Vila, Marta; Gonzalez Bermudez, Meritxell
    Sixth International Workshop on Computational Semantics
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • The project HOPS: Enabling an Intelligent Natural Language Based Hub for the Deployment of Advanced Semantically Enriched Multi-channel Mass-scale Online Public Services

     Gatius Vila, Marta; Gonzalez Bermudez, Meritxell
    21st Congreso de la Sociedad Española para el Procesamiento del Lenguaje Natural
    Presentation's date: 2005-09-14
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Towards the Standardisation of Thermodynamic and Physical Properties Packages

     Espuña Camarasa, Antonio; Puigjaner Corbella, Luis; Benqlilou, Chouaib; Gonzalez Bermudez, Meritxell
    European Symposium on Computer-Aided Process Engineering-14
    Presentation's date: 2004-05-18
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Utilización de ontologías en el desarrollo de sistemas de diálogo

     Gatius Vila, Marta; Gonzalez Bermudez, Meritxell
    Jornadas en Tecnología del Habla
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Access to the full text
    Ontology-driven voiceXML dialogues generation  Open access

     Gatius Vila, Marta; Gonzalez Bermudez, Meritxell
    Berliner XML - Tage
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    This paper describes a proposal to improve the communication process and the engineering features in VoiceXML dialogues. This proposal is focused on the efficient and reusable representation of the knowledge involved in communication. In order to achieve a good dialogue design we propose the explicit representation of the conceptual information the application needs form the user in an ontology. A syntactic-semantic taxonomy is provided to facilitate the generation of the grammars and the system's messages. Using this separate, reusable knowledge organization, VoiceXML dialogues for different applications and in different languages can be generated semi-automatically.

    This paper describes a proposal to improve the communication process and the engineering features in VoiceXML dialogues. This proposal is focused on the efficient and reusable representation of the knowledge involved in communication. In order to achieve a good dialogue design we propose the explicit representation of the conceptual information the application needs form the user in an ontology. A syntactic-semantic taxonomy is provided to facilitate the generation of the grammars and the system's messages. Using this separate, reusable knowledge organization, VoiceXML dialogues for different applications and in different languages can be generated semi-automatically.