34 resultados para Human Language Technologies
em Universidad Politécnica de Madrid
Resumo:
OntoTag - A Linguistic and Ontological Annotation Model Suitable for the Semantic Web
1. INTRODUCTION. LINGUISTIC TOOLS AND ANNOTATIONS: THEIR LIGHTS AND SHADOWS
Computational Linguistics is already a consolidated research area. It builds upon the results of other two major ones, namely Linguistics and Computer Science and Engineering, and it aims at developing computational models of human language (or natural language, as it is termed in this area). Possibly, its most well-known applications are the different tools developed so far for processing human language, such as machine translation systems and speech recognizers or dictation programs.
These tools for processing human language are commonly referred to as linguistic tools. Apart from the examples mentioned above, there are also other types of linguistic tools that perhaps are not so well-known, but on which most of the other applications of Computational Linguistics are built. These other types of linguistic tools comprise POS taggers, natural language parsers and semantic taggers, amongst others. All of them can be termed linguistic annotation tools.
Linguistic annotation tools are important assets. In fact, POS and semantic taggers (and, to a lesser extent, also natural language parsers) have become critical resources for the computer applications that process natural language. Hence, any computer application that has to analyse a text automatically and ‘intelligently’ will include at least a module for POS tagging. The more an application needs to ‘understand’ the meaning of the text it processes, the more linguistic tools and/or modules it will incorporate and integrate.
However, linguistic annotation tools have still some limitations, which can be summarised as follows:
1. Normally, they perform annotations only at a certain linguistic level (that is, Morphology, Syntax, Semantics, etc.).
2. They usually introduce a certain rate of errors and ambiguities when tagging. This error rate ranges from 10 percent up to 50 percent of the units annotated for unrestricted, general texts.
3. Their annotations are most frequently formulated in terms of an annotation schema designed and implemented ad hoc.
A priori, it seems that the interoperation and the integration of several linguistic tools into an appropriate software architecture could most likely solve the limitations stated in (1). Besides, integrating several linguistic annotation tools and making them interoperate could also minimise the limitation stated in (2). Nevertheless, in the latter case, all these tools should produce annotations for a common level, which would have to be combined in order to correct their corresponding errors and inaccuracies. Yet, the limitation stated in (3) prevents both types of integration and interoperation from being easily achieved.
In addition, most high-level annotation tools rely on other lower-level annotation tools and their outputs to generate their own ones. For example, sense-tagging tools (operating at the semantic level) often use POS taggers (operating at a lower level, i.e., the morphosyntactic) to identify the grammatical category of the word or lexical unit they are annotating. Accordingly, if a faulty or inaccurate low-level annotation tool is to be used by other higher-level one in its process, the errors and inaccuracies of the former should be minimised in advance. Otherwise, these errors and inaccuracies would be transferred to (and even magnified in) the annotations of the high-level annotation tool.
Therefore, it would be quite useful to find a way to
(i) correct or, at least, reduce the errors and the inaccuracies of lower-level linguistic tools;
(ii) unify the annotation schemas of different linguistic annotation tools or, more generally speaking, make these tools (as well as their annotations) interoperate.
Clearly, solving (i) and (ii) should ease the automatic annotation of web pages by means of linguistic tools, and their transformation into Semantic Web pages (Berners-Lee, Hendler and Lassila, 2001). Yet, as stated above, (ii) is a type of interoperability problem. There again, ontologies (Gruber, 1993; Borst, 1997) have been successfully applied thus far to solve several interoperability problems. Hence, ontologies should help solve also the problems and limitations of linguistic annotation tools aforementioned.
Thus, to summarise, the main aim of the present work was to combine somehow these separated approaches, mechanisms and tools for annotation from Linguistics and Ontological Engineering (and the Semantic Web) in a sort of hybrid (linguistic and ontological) annotation model, suitable for both areas. This hybrid (semantic) annotation model should (a) benefit from the advances, models, techniques, mechanisms and tools of these two areas; (b) minimise (and even solve, when possible) some of the problems found in each of them; and (c) be suitable for the Semantic Web. The concrete goals that helped attain this aim are presented in the following section.
2. GOALS OF THE PRESENT WORK
As mentioned above, the main goal of this work was to specify a hybrid (that is, linguistically-motivated and ontology-based) model of annotation suitable for the Semantic Web (i.e. it had to produce a semantic annotation of web page contents). This entailed that the tags included in the annotations of the model had to (1) represent linguistic concepts (or linguistic categories, as they are termed in ISO/DCR (2008)), in order for this model to be linguistically-motivated; (2) be ontological terms (i.e., use an ontological vocabulary), in order for the model to be ontology-based; and (3) be structured (linked) as a collection of ontology-based
Resumo:
We present two approaches to cluster dialogue-based information obtained by the speech understanding module and the dialogue manager of a spoken dialogue system. The purpose is to estimate a language model related to each cluster, and use them to dynamically modify the model of the speech recognizer at each dialogue turn. In the first approach we build the cluster tree using local decisions based on a Maximum Normalized Mutual Information criterion. In the second one we take global decisions, based on the optimization of the global perplexity of the combination of the cluster-related LMs. Our experiments show a relative reduction of the word error rate of 15.17%, which helps to improve the performance of the understanding and the dialogue manager modules.
Resumo:
La diabetes mellitus es un trastorno del metabolismo de los carbohidratos producido por la insuficiente o nula producción de insulina o la reducida sensibilidad a esta hormona. Es una enfermedad crónica con una mayor prevalencia en los países desarrollados debido principalmente a la obesidad, la vida sedentaria y disfunciones en el sistema endocrino relacionado con el páncreas. La diabetes Tipo 1 es una enfermedad autoinmune en la que son destruidas las células beta del páncreas, que producen la insulina, y es necesaria la administración de insulina exógena. Un enfermo de diabetes Tipo 1 debe seguir una terapia con insulina administrada por la vía subcutánea que debe estar adaptada a sus necesidades metabólicas y a sus hábitos de vida, esta terapia intenta imitar el perfil insulínico de un páncreas no patológico. La tecnología actual permite abordar el desarrollo del denominado “páncreas endocrino artificial”, que aportaría precisión, eficacia y seguridad para los pacientes, en cuanto a la normalización del control glucémico y reducción del riesgo de hipoglucemias. Permitiría que el paciente no estuviera tan pendiente de su enfermedad. El páncreas artificial consta de un sensor continuo de glucosa, una bomba de infusión de insulina y un algoritmo de control, que calcula la insulina a infusionar usando la glucosa como información principal. Este trabajo presenta un método de control en lazo semi-cerrado mediante un sistema borroso experto basado en reglas. La regulación borrosa se fundamenta en la ambigüedad del lenguaje del ser humano. Esta incertidumbre sirve para la formación de una serie de reglas que representan el pensamiento humano, pero a la vez es el sistema que controla un proceso, en este caso el sistema glucorregulatorio. Este proyecto está enfocado en el diseño de un controlador borroso que haciendo uso de variables como la glucosa, insulina y dieta, sea capaz de restaurar la función endocrina del páncreas de forma tecnológica. La validación del algoritmo se ha realizado principalmente mediante experimentos en simulación utilizando una población de pacientes sintéticos, evaluando los resultados con estadísticos de primer orden y algunos más específicos como el índice de riesgo de Kovatchev, para después comparar estos resultados con los obtenidos por otros métodos de control anteriores. Los resultados demuestran que el control borroso (FBPC) mejora el control glucémico con respecto a un sistema predictivo experto basado en reglas booleanas (pBRES). El FBPC consigue reducir siempre la glucosa máxima y aumentar la mínima respecto del pBRES pero es en terapias desajustadas, donde el FBPC es especialmente robusto, hace descender la glucosa máxima 8,64 mg/dl, el uso de insulina es 3,92 UI menor, aumenta la glucosa mínima 3,32 mg/dl y lleva al rango de glucosa 80 – 110 mg/dl 15,33 muestras más. Por lo tanto se puede concluir que el FBPC realiza un mejor control glucémico que el controlador pBRES haciéndole especialmente efectivo, robusto y seguro en condiciones de desajustes de terapia basal y con gran capacidad de mejora futura. SUMMARY The diabetes mellitus is a metabolic disorder caused by a poor or null insulin secretion or a reduced sensibility to insulin. Diabetes is a chronic disease with a higher prevalence in the industrialized countries, mainly due to obesity, the sedentary life and endocrine disfunctions connected with the pancreas. Type 1 diabetes is a self-immune disease where the beta cells of the pancreas, which are the responsible of secreting insulin, are damaged. Hence, it is necessary an exogenous delivery of insulin. The Type 1 diabetic patient has to follow a therapy with subcutaneous insulin administration which should be adjusted to his/her metabolic needs and life style. This therapy tries to mimic the insulin profile of a non-pathological pancreas. Current technology lets the development of the so-called endocrine artificial pancreas that would provide accuracy, efficiency and safety to patients, in regards to the glycemic control normalization and reduction of the risk of hypoglycemic. In addition, it would help the patient not to be so concerned about his disease. The artificial pancreas has a continuous glucose sensor, an insulin infusion pump and a control algorithm, that calculates the insulin infusion using the glucose as main information. This project presents a method of control in semi-closed-loop, through an expert fuzzy system based on rules. The fuzzy regulation is based on the human language ambiguity. This uncertainty serves for construction of some rules that represent the human language besides it is the system that controls a process, in this case the glucoregulatory system. This project is focus on the design of a fuzzy controller that, using variables like glucose insulin and diet, will be able to restore the pancreas endocrine function with technology. The algorithm assessment has mainly been done through experiments in simulation using a population of synthetic patients, evaluating the results with first order statistical parameters and some other more specific such as the Kovatchev risk index, to compare later these results with the ones obtained in others previous methods of control. The results demonstrate that the fuzzy control (FBPC) improves the glycemic control connected with a predictive expert system based on Booleans rules (pBRES). The FBPC is always able to reduce the maximum level of glucose and increase the minimum level as compared with pBRES but it is in unadjusted therapies where FBPC is especially strong, it manages to decrease the maximum level of glucose and insulin used by 8,64 mg/dl and 3,92 UI respectively, also increases the value of minimum glucose by 3,32 mg/dl, getting 15,33 samples more inside the 80-110 mg/dl glucose rank. Therefore we can conclude that FBPC achieves a better glycemic control than the controller pBRES doing it especially effective, robust and safe in conditions of mismatch basal therapy and with a great capacity for future improvements.
Resumo:
La idea de dotar a un grupo de robots o agentes artificiales de un lenguaje ha sido objeto de intenso estudio en las ultimas décadas. Como no podía ser de otra forma los primeros intentos se enfocaron hacia el estudio de la emergencia de vocabularios compartidos convencionalmente por el grupo de robots. Las ventajas que puede ofrecer un léxico común son evidentes, como también lo es que un lenguaje con una estructura más compleja, en la que se pudieran combinar palabras, sería todavía más beneficioso. Surgen así algunas propuestas enfocadas hacia la emergencia de un lenguaje consensuado que muestre una estructura sintáctica similar al lenguaje humano, entre las que se encuentra este trabajo. Tomar el lenguaje humano como modelo supone adoptar algunas de las hipótesis y teorías que disciplinas como la filosofía, la psicología o la lingüística entre otras se han encargado de proponer. Según estas aproximaciones teóricas el lenguaje presenta una doble dimension formal y funcional. En base a su dimensión formal parece claro que el lenguaje sigue unas reglas, por lo que el uso de una gramática se ha considerado esencial para su representación, pero también porque las gramáticas son un dispositivo muy sencillo y potente que permite generar fácilmente estructuras simbólicas. En cuanto a la dimension funcional se ha tenido en cuenta la teoría quizá más influyente de los últimos tiempos, que no es otra que la Teoría de los Actos del Habla. Esta teoría se basa en la idea de Wittgenstein por la que el significado reside en el uso del lenguaje, hasta el punto de que éste se entiende como una manera de actuar y de comportarse, en definitiva como una forma de vida. Teniendo presentes estas premisas en esta tesis se pretende experimentar con modelos computacionales que permitan a un grupo de robots alcanzar un lenguaje común de manera autónoma, simplemente mediante interacciones individuales entre los robots, en forma de juegos de lenguaje. Para ello se proponen tres modelos distintos de lenguaje: • Un modelo basado en gramáticas probabilísticas y aprendizaje por refuerzo en el que las interacciones y el uso del lenguaje son claves para su emergencia y que emplea una gramática generativa estática y diseñada de antemano. Este modelo se aplica a dos grupos distintos: uno formado exclusivamente por robots y otro que combina robots y un humano, de manera que en este segundo caso se plantea un aprendizaje supervisado por humanos. • Un modelo basado en evolución gramatical que permite estudiar no solo el consenso sintáctico, sino también cuestiones relativas a la génesis del lenguaje y que emplea una gramática universal a partir de la cual los robots pueden evolucionar por sí mismos la gramática más apropiada según la situación lingüística que traten en cada momento. • Un modelo basado en evolución gramatical y aprendizaje por refuerzo que toma aspectos de los anteriores y amplia las posibilidades de los robots al permitir desarrollar un lenguaje que se adapta a situaciones lingüísticas dinámicas que pueden cambiar en el tiempo y también posibilita la imposición de restricciones de orden muy frecuentes en las estructuras sintácticas complejas. Todos los modelos implican un planteamiento descentralizado y auto-organizado, de manera que ninguno de los robots es el dueño del lenguaje y todos deben cooperar y colaborar de forma coordinada para lograr el consenso sintáctico. En cada caso se plantean experimentos que tienen como objetivo validar los modelos propuestos, tanto en lo relativo al éxito en la emergencia del lenguaje como en lo relacionado con cuestiones paralelas de importancia, como la interacción hombre-máquina o la propia génesis del lenguaje. ABSTRACT The idea of giving a language to a group of robots or artificial agents has been the subject of intense study in recent decades. The first attempts have focused on the development and emergence of a conventionally shared vocabulary. The advantages that can provide a common vocabulary are evident and therefore a more complex language that combines words would be even more beneficial. Thus some proposals are put forward towards the emergence of a consensual language with a sintactical structure in similar terms to the human language. This work follows this trend. Taking the human language as a model means taking some of the assumptions and theories that disciplines such as philosophy, psychology or linguistics among others have provided. According to these theoretical positions language has a double formal and functional dimension. Based on its formal dimension it seems clear that language follows rules, so that the use of a grammar has been considered essential for representation, but also because grammars are a very simple and powerful device that easily generates these symbolic structures. As for the functional dimension perhaps the most influential theory of recent times, the Theory of Speech Acts has been taken into account. This theory is based on the Wittgenstein’s idea about that the meaning lies in the use of language, to the extent that it is understood as a way of acting and behaving. Having into account these issues this work implements some computational models in order to test if they allow a group of robots to reach in an autonomous way a shared language by means of individual interaction among them, that is by means of language games. Specifically, three different models of language for robots are proposed: • A reinforcement learning based model in which interactions and language use are key to its emergence. This model uses a static probabilistic generative grammar which is designed beforehand. The model is applied to two different groups: one formed exclusively by robots and other combining robots and a human. Therefore, in the second case the learning process is supervised by the human. • A model based on grammatical evolution that allows us to study not only the syntactic consensus, but also the very genesis of language. This model uses a universal grammar that allows robots to evolve for themselves the most appropriate grammar according to the current linguistic situation they deal with. • A model based on grammatical evolution and reinforcement learning that takes aspects of the previous models and increases their possibilities. This model allows robots to develop a language in order to adapt to dynamic language situations that can change over time and also allows the imposition of syntactical order restrictions which are very common in complex syntactic structures. All models involve a decentralized and self-organized approach so that none of the robots is the language’s owner and everyone must cooperate and work together in a coordinated manner to achieve syntactic consensus. In each case experiments are presented in order to validate the proposed models, both in terms of success about the emergence of language and it relates to the study of important parallel issues, such as human-computer interaction or the very genesis of language.
Resumo:
The application of Linked Data technology to the publication of linguistic data promises to facilitate interoperability of these data and has lead to the emergence of the so called Linguistic Linked Data Cloud (LLD) in which linguistic data is published following the Linked Data principles. Three essential issues need to be addressed for such data to be easily exploitable by language technologies: i) appropriate machine-readable licensing information is needed for each dataset, ii) minimum quality standards for Linguistic Linked Data need to be defined, and iii) appropriate vocabularies for publishing Linguistic Linked Data resources are needed. We propose the notion of Licensed Linguistic Linked Data (3LD) in which different licensing models might co-exist, from totally open to more restrictive licenses through to completely closed datasets.
Resumo:
El proyecto nace de un proyecto anterior donde se construyó un modelo para representar la información de los estudios superiores mediante una red de ontologías, proporcionando una definición común de conceptos importantes. Este proyecto consiste en desarrollar una herramienta capaz de generar datos educativos, a partir de la red de ontologías mencionadas anteriormente, siguiendo el paradigma de Linked Data [1]. La herramienta deberá extraer datos de diferentes fuentes educativas y transformará dichos datos educativos a datos enlazados (Linked Data). Para llevar a cabo esta labor se ha utilizado GATE Developer [2], es un entorno de desarrollo que proporciona un completo conjunto de herramientas gráficas interactivas para la creación, medición y mantenimiento de componentes de software para el procesamiento del lenguaje humano.---ABSTRACT---The project arises from a previous project in which a model was constructed to represent information of higher education through a network of ontologies, providing a common definition of important concepts. This project is to develop a tool capable of generating educational data from the ontology network mentioned above, following the paradigm of Linked Data [1]. The tool will extract data from different educational sources and transform said data to linked data (linked data). To carry out this work has been used GATE Developer [2]. It is a development environment that provides a comprehensive set of interactive graphical tools for creating, measuring and maintenance of software components for human language processing.
Resumo:
En esta Tesis se presentan dos líneas de investigación relacionadas y que contribuyen a las áreas de Interacción Hombre-Tecnología (o Máquina; siglas en inglés: HTI o HMI), lingüística computacional y evaluación de la experiencia del usuario. Las dos líneas en cuestión son el diseño y la evaluación centrada en el usuario de sistemas de Interacción Hombre-Máquina avanzados. En la primera parte de la Tesis (Capítulos 2 a 4) se abordan cuestiones fundamentales del diseño de sistemas HMI avanzados. El Capítulo 2 presenta una panorámica del estado del arte de la investigación en el ámbito de los sistemas conversacionales multimodales, con la que se enmarca el trabajo de investigación presentado en el resto de la Tesis. Los Capítulos 3 y 4 se centran en dos grandes aspectos del diseño de sistemas HMI: un gestor del diálogo generalizado para tratar la Interacción Hombre-Máquina multimodal y sensible al contexto, y el uso de agentes animados personificados (ECAs) para mejorar la robustez del diálogo, respectivamente. El Capítulo 3, sobre gestión del diálogo, aborda el tratamiento de la heterogeneidad de la información proveniente de las modalidades comunicativas y de los sensores externos. En este capítulo se propone, en un nivel de abstracción alto, una arquitectura para la gestión del diálogo con influjos heterogéneos de información, apoyándose en el uso de State Chart XML. En el Capítulo 4 se presenta una contribución a la representación interna de intenciones comunicativas, y su traducción a secuencias de gestos a ejecutar por parte de un ECA, diseñados específicamente para mejorar la robustez en situaciones de diálogo críticas que pueden surgir, por ejemplo, cuando se producen errores de entendimiento en la comunicación entre el usuario humano y la máquina. Se propone, en estas páginas, una extensión del Functional Mark-up Language definido en el marco conceptual SAIBA. Esta extensión permite representar actos comunicativos que realizan intenciones del emisor (la máquina) que no se pretende sean captadas conscientemente por el receptor (el usuario humano), pero con las que se pretende influirle a éste e influir el curso del diálogo. Esto se consigue mediante un objeto llamado Base de Intenciones Comunicativas (en inglés, Communication Intention Base, o CIB). La representación en el CIB de intenciones “no claradas” además de las explícitas permite la construcción de actos comunicativos que realizan simultáneamente varias intenciones comunicativas. En el Capítulo 4 también se describe un sistema experimental para el control remoto (simulado) de un asistente domótico, con autenticación de locutor para dar acceso, y con un ECA en el interfaz de cada una de estas tareas. Se incluye una descripción de las secuencias de comportamiento verbal y no verbal de los ECAs, que fueron diseñados específicamente para determinadas situaciones con objeto de mejorar la robustez del diálogo. Los Capítulos 5 a 7 conforman la parte de la Tesis dedicada a la evaluación. El Capítulo 5 repasa antecedentes relevantes en la literatura de tecnologías de la información en general, y de sistemas de interacción hablada en particular. Los principales antecedentes en el ámbito de la evaluación de la interacción sobre los cuales se ha desarrollado el trabajo presentado en esta Tesis son el Technology Acceptance Model (TAM), la herramienta Subjective Assessment of Speech System Interfaces (SASSI), y la Recomendación P.851 de la ITU-T. En el Capítulo 6 se describen un marco y una metodología de evaluación aplicados a la experiencia del usuario con sistemas HMI multimodales. Se desarrolló con este propósito un novedoso marco de evaluación subjetiva de la calidad de la experiencia del usuario y su relación con la aceptación por parte del mismo de la tecnología HMI (el nombre dado en inglés a este marco es Subjective Quality Evaluation Framework). En este marco se articula una estructura de clases de factores subjetivos relacionados con la satisfacción y aceptación por parte del usuario de la tecnología HMI propuesta. Esta estructura, tal y como se propone en la presente tesis, tiene dos dimensiones ortogonales. Primero se identifican tres grandes clases de parámetros relacionados con la aceptación por parte del usuario: “agradabilidad ” (likeability: aquellos que tienen que ver con la experiencia de uso, sin entrar en valoraciones de utilidad), rechazo (los cuales sólo pueden tener una valencia negativa) y percepción de utilidad. En segundo lugar, este conjunto clases se reproduce para distintos “niveles, o focos, percepción del usuario”. Éstos incluyen, como mínimo, un nivel de valoración global del sistema, niveles correspondientes a las tareas a realizar y objetivos a alcanzar, y un nivel de interfaz (en los casos propuestos en esta tesis, el interfaz es un sistema de diálogo con o sin un ECA). En el Capítulo 7 se presenta una evaluación empírica del sistema descrito en el Capítulo 4. El estudio se apoya en los mencionados antecedentes en la literatura, ampliados con parámetros para el estudio específico de los agentes animados (los ECAs), la auto-evaluación de las emociones de los usuarios, así como determinados factores de rechazo (concretamente, la preocupación por la privacidad y la seguridad). También se evalúa el marco de evaluación subjetiva de la calidad propuesto en el capítulo anterior. Los análisis de factores efectuados revelan una estructura de parámetros muy cercana conceptualmente a la división de clases en utilidad-agradabilidad-rechazo propuesta en dicho marco, resultado que da cierta validez empírica al marco. Análisis basados en regresiones lineales revelan estructuras de dependencias e interrelación entre los parámetros subjetivos y objetivos considerados. El efecto central de mediación, descrito en el Technology Acceptance Model, de la utilidad percibida sobre la relación de dependencia entre la intención de uso y la facilidad de uso percibida, se confirma en el estudio presentado en la presente Tesis. Además, se ha encontrado que esta estructura de relaciones se fortalece, en el estudio concreto presentado en estas páginas, si las variables consideradas se generalizan para cubrir más ampliamente las categorías de agradabilidad y utilidad contempladas en el marco de evaluación subjetiva de calidad. Se ha observado, asimismo, que los factores de rechazo aparecen como un componente propio en los análisis de factores, y además se distinguen por su comportamiento: moderan la relación entre la intención de uso (que es el principal indicador de la aceptación del usuario) y su predictor más fuerte, la utilidad percibida. Se presentan también resultados de menor importancia referentes a los efectos de los ECAs sobre los interfaces de los sistemas de diálogo y sobre los parámetros de percepción y las valoraciones de los usuarios que juegan un papel en conformar su aceptación de la tecnología. A pesar de que se observa un rendimiento de la interacción dialogada ligeramente mejor con ECAs, las opiniones subjetivas son muy similares entre los dos grupos experimentales (uno interactuando con un sistema de diálogo con ECA, y el otro sin ECA). Entre las pequeñas diferencias encontradas entre los dos grupos destacan las siguientes: en el grupo experimental sin ECA (es decir, con interfaz sólo de voz) se observó un efecto más directo de los problemas de diálogo (por ejemplo, errores de reconocimiento) sobre la percepción de robustez, mientras que el grupo con ECA tuvo una respuesta emocional más positiva cuando se producían problemas. Los ECAs parecen generar inicialmente expectativas más elevadas en cuanto a las capacidades del sistema, y los usuarios de este grupo se declaran más seguros de sí mismos en su interacción. Por último, se observan algunos indicios de efectos sociales de los ECAs: la “amigabilidad ” percibida los ECAs estaba correlada con un incremento la preocupación por la seguridad. Asimismo, los usuarios del sistema con ECAs tendían más a culparse a sí mismos, en lugar de culpar al sistema, de los problemas de diálogo que pudieran surgir, mientras que se observó una ligera tendencia opuesta en el caso de los usuarios del sistema con interacción sólo de voz. ABSTRACT This Thesis presents two related lines of research work contributing to the general fields of Human-Technology (or Machine) Interaction (HTI, or HMI), computational linguistics, and user experience evaluation. These two lines are the design and user-focused evaluation of advanced Human-Machine (or Technology) Interaction systems. The first part of the Thesis (Chapters 2 to 4) is centred on advanced HMI system design. Chapter 2 provides a background overview of the state of research in multimodal conversational systems. This sets the stage for the research work presented in the rest of the Thesis. Chapers 3 and 4 focus on two major aspects of HMI design in detail: a generalised dialogue manager for context-aware multimodal HMI, and embodied conversational agents (ECAs, or animated agents) to improve dialogue robustness, respectively. Chapter 3, on dialogue management, deals with how to handle information heterogeneity, both from the communication modalities or from external sensors. A highly abstracted architectural contribution based on State Chart XML is proposed. Chapter 4 presents a contribution for the internal representation of communication intentions and their translation into gestural sequences for an ECA, especially designed to improve robustness in critical dialogue situations such as when miscommunication occurs. We propose an extension of the functionality of Functional Mark-up Language, as envisaged in much of the work in the SAIBA framework. Our extension allows the representation of communication acts that carry intentions that are not for the interlocutor to know of, but which are made to influence him or her as well as the flow of the dialogue itself. This is achieved through a design element we have called the Communication Intention Base. Such r pr s ntation of “non- clar ” int ntions allows th construction of communication acts that carry several communication intentions simultaneously. Also in Chapter 4, an experimental system is described which allows (simulated) remote control to a home automation assistant, with biometric (speaker) authentication to grant access, featuring embodied conversation agents for each of the tasks. The discussion includes a description of the behavioural sequences for the ECAs, which were designed for specific dialogue situations with particular attention given to the objective of improving dialogue robustness. Chapters 5 to 7 form the evaluation part of the Thesis. Chapter 5 reviews evaluation approaches in the literature for information technologies, as well as in particular for speech-based interaction systems, that are useful precedents to the contributions of the present Thesis. The main evaluation precedents on which the work in this Thesis has built are the Technology Acceptance Model (TAM), the Subjective Assessment of Speech System Interfaces (SASSI) tool, and ITU-T Recommendation P.851. Chapter 6 presents the author’s work in establishing an valuation framework and methodology applied to the users’ experience with multimodal HMI systems. A novel user-acceptance Subjective Quality Evaluation Framework was developed by the author specifically for this purpose. A class structure arises from two orthogonal sets of dimensions. First we identify three broad classes of parameters related with user acceptance: likeability factors (those that have to do with the experience of using the system), rejection factors (which can only have a negative valence) and perception of usefulness. Secondly, the class structure is further broken down into several “user perception levels”; at the very least: an overall system-assessment level, task and goal-related levels, and an interface level (e.g., a dialogue system with or without an ECA). An empirical evaluation of the system described in Chapter 4 is presented in Chapter 7. The study was based on the abovementioned precedents in the literature, expanded with categories covering the inclusion of an ECA, the users’ s lf-assessed emotions, and particular rejection factors (privacy and security concerns). The Subjective Quality Evaluation Framework proposed in the previous chapter was also scrutinised. Factor analyses revealed an item structure very much related conceptually to the usefulness-likeability-rejection class division introduced above, thus giving it some empirical weight. Regression-based analysis revealed structures of dependencies, paths of interrelations, between the subjective and objective parameters considered. The central mediation effect, in the Technology Acceptance Model, of perceived usefulness on the dependency relationship of intention-to-use with perceived ease of use was confirmed in this study. Furthermore, the pattern of relationships was stronger for variables covering more broadly the likeability and usefulness categories in the Subjective Quality Evaluation Framework. Rejection factors were found to have a distinct presence as components in factor analyses, as well as distinct behaviour: they were found to moderate the relationship between intention-to-use (the main measure of user acceptance) and its strongest predictor, perceived usefulness. Insights of secondary importance are also given regarding the effect of ECAs on the interface of spoken dialogue systems and the dimensions of user perception and judgement attitude that may have a role in determining user acceptance of the technology. Despite observing slightly better performance values in the case of the system with the ECA, subjective opinions regarding both systems were, overall, very similar. Minor differences between two experimental groups (one interacting with an ECA, the other only through speech) include a more direct effect of dialogue problems (e.g., non-understandings) on perceived dialogue robustness for the voice-only interface test group, and a more positive emotional response for the ECA test group. Our findings further suggest that the ECA generates higher initial expectations, and users seem slightly more confident in their interaction with the ECA than do those without it. Finally, mild evidence of social effects of ECAs was also found: the perceived friendliness of the ECA increased security concerns, and ECA users may tend to blame themselves rather than the system when dialogue problems are encountered, while the opposite may be true for voice-only users.
Resumo:
Current “Internet of Things” concepts point to a future where connected objects gather meaningful information about their environment and share it with other objects and people. In particular, objects embedding Human Machine Interaction (HMI), such as mobile devices and, increasingly, connected vehicles, home appliances, urban interactive infrastructures, etc., may not only be conceived as sources of sensor information, but, through interaction with their users, they can also produce highly valuable context-aware human-generated observations. We believe that the great promise offered by combining and sharing all of the different sources of information available can be realized through the integration of HMI and Semantic Sensor Web technologies. This paper presents a technological framework that harmonizes two of the most influential HMI and Sensor Web initiatives: the W3C’s Multimodal Architecture and Interfaces (MMI) and the Open Geospatial Consortium (OGC) Sensor Web Enablement (SWE) with its semantic extension, respectively. Although the proposed framework is general enough to be applied in a variety of connected objects integrating HMI, a particular development is presented for a connected car scenario where drivers’ observations about the traffic or their environment are shared across the Semantic Sensor Web. For implementation and evaluation purposes an on-board OSGi (Open Services Gateway Initiative) architecture was built, integrating several available HMI, Sensor Web and Semantic Web technologies. A technical performance test and a conceptual validation of the scenario with potential users are reported, with results suggesting the approach is sound
Resumo:
This paper describes a preprocessing module for improving the performance of a Spanish into Spanish Sign Language (Lengua de Signos Espanola: LSE) translation system when dealing with sparse training data. This preprocessing module replaces Spanish words with associated tags. The list with Spanish words (vocabulary) and associated tags used by this module is computed automatically considering those signs that show the highest probability of being the translation of every Spanish word. This automatic tag extraction has been compared to a manual strategy achieving almost the same improvement. In this analysis, several alternatives for dealing with non-relevant words have been studied. Non-relevant words are Spanish words not assigned to any sign. The preprocessing module has been incorporated into two well-known statistical translation architectures: a phrase-based system and a Statistical Finite State Transducer (SFST). This system has been developed for a specific application domain: the renewal of Identity Documents and Driver's License. In order to evaluate the system a parallel corpus made up of 4080 Spanish sentences and their LSE translation has been used. The evaluation results revealed a significant performance improvement when including this preprocessing module. In the phrase-based system, the proposed module has given rise to an increase in BLEU (Bilingual Evaluation Understudy) from 73.8% to 81.0% and an increase in the human evaluation score from 0.64 to 0.83. In the case of SFST, BLEU increased from 70.6% to 78.4% and the human evaluation score from 0.65 to 0.82.
Resumo:
Speech Technologies can provide important benefits for the development of more usable and safe in-vehicle human-machine interactive systems (HMIs). However mainly due robustness issues, the use of spoken interaction can entail important distractions to the driver. In this challenging scenario, while speech technologies are evolving, further research is necessary to explore how they can be complemented with both other modalities (multimodality) and information from the increasing number of available sensors (context-awareness). The perceived quality of speech technologies can significantly be increased by implementing such policies, which simply try to make the best use of all the available resources; and the in vehicle scenario is an excellent test-bed for this kind of initiatives. In this contribution we propose an event-based HMI design framework which combines context modelling and multimodal interaction using a W3C XML language known as SCXML. SCXML provides a general process control mechanism that is being considered by W3C to improve both voice interaction (VoiceXML) and multimodal interaction (MMI). In our approach we try to anticipate and extend these initiatives presenting a flexible SCXML-based approach for the design of a wide range of multimodal context-aware HMI in-vehicle interfaces. The proposed framework for HMI design and specification has been implemented in an automotive OSGi service platform, and it is being used and tested in the Spanish research project MARTA for the development of several in-vehicle interactive applications.
Resumo:
This paper describes an infrastructure for the automated evaluation of semantic technologies and, in particular, semantic search technologies. For this purpose, we present an evaluation framework which follows a service-oriented approach for evaluating semantic technologies and uses the Business Process Execution Language (BPEL) to define evaluation workflows that can be executed by process engines. This framework supports a variety of evaluations, from different semantic areas, including search, and is extendible to new evaluations. We show how BPEL addresses this diversity as well as how it is used to solve specific challenges such as heterogeneity, error handling and reuse
Resumo:
Systems of Systems (SoS) present challenging features and existing tools result often inadequate for their analysis, especially for heteregeneous networked infrastructures. Most accident scenarios in networked systems cannot be addressed by a simplistic black or white (i.e. functioning or failed) approach. Slow deviations from nominal operation conditions may cause degraded behaviours that suddenly end up into unexpected malfunctioning, with large portions of the network affected. In this paper,we present a language for modelling networked SoS. The language makes it possible to represent interdependencies of various natures, e.g. technical, organizational and human. The representation of interdependencies is based on control relationships that exchange physical quantities and related information. The language also makes it possible the identification of accident scenarios, by representing the propagation of failure events throughout the network. The results can be used for assessing the effectiveness of those mechanisms and measures that contribute to the overall resilience, both in qualitative and quantitative terms. The presented modelling methodology is general enough to be applied in combination with already existing system analysis techniques, such as risk assessment, dependability and performance evaluation
Resumo:
This paper describes a categorization module for improving the performance of a Spanish into Spanish Sign Language (LSE) translation system. This categorization module replaces Spanish words with associated tags. When implementing this module, several alternatives for dealing with non-relevant words have been studied. Non-relevant words are Spanish words not relevant in the translation process. The categorization module has been incorporated into a phrase-based system and a Statistical Finite State Transducer (SFST). The evaluation results reveal that the BLEU has increased from 69.11% to 78.79% for the phrase-based system and from 69.84% to 75.59% for the SFST.
Resumo:
The design and development of spoken interaction systems has been a thoroughly studied research scope for the last decades. The aim is to obtain systems with the ability to interact with human agents with a high degree of naturalness and efficiency, allowing them to carry out the actions they desire using speech, as it is the most natural means of communication between humans. To achieve that degree of naturalness, it is not enough to endow systems with the ability to accurately understand the user’s utterances and to properly react to them, even considering the information provided by the user in his or her previous interactions. The system has also to be aware of the evolution of the conditions under which the interaction takes place, in order to act the most coherent way as possible at each moment. Consequently, one of the most important features of the system is that it has to be context-aware. This context awareness of the system can be reflected in the modification of the behaviour of the system taking into account the current situation of the interaction. For instance, the system should decide which action it has to carry out, or the way to perform it, depending on the user that requests it, on the way that the user addresses the system, on the characteristics of the environment in which the interaction takes place, and so on. In other words, the system has to adapt its behaviour to these evolving elements of the interaction. Moreover that adaptation has to be carried out, if possible, in such a way that the user: i) does not perceive that the system has to make any additional effort, or to devote interaction time to perform tasks other than carrying out the requested actions, and ii) does not have to provide the system with any additional information to carry out the adaptation, which could imply a lesser efficiency of the interaction, since users should devote several interactions only to allow the system to become adapted. In the state-of-the-art spoken dialogue systems, researchers have proposed several disparate strategies to adapt the elements of the system to different conditions of the interaction (such as the acoustic characteristics of a specific user’s speech, the actions previously requested, and so on). Nevertheless, to our knowledge there is not any consensus on the procedures to carry out these adaptation. The approaches are to an extent unrelated from one another, in the sense that each one considers different pieces of information, and the treatment of that information is different taking into account the adaptation carried out. In this regard, the main contributions of this Thesis are the following ones: Definition of a contextualization framework. We propose a unified approach that can cover any strategy to adapt the behaviour of a dialogue system to the conditions of the interaction (i.e. the context). In our theoretical definition of the contextualization framework we consider the system’s context as all the sources of variability present at any time of the interaction, either those ones related to the environment in which the interaction takes place, or to the human agent that addresses the system at each moment. Our proposal relies on three aspects that any contextualization approach should fulfill: plasticity (i.e. the system has to be able to modify its behaviour in the most proactive way taking into account the conditions under which the interaction takes place), adaptivity (i.e. the system has also to be able to consider the most appropriate sources of information at each moment, both environmental and user- and dialogue-dependent, to effectively adapt to the conditions aforementioned), and transparency (i.e. the system has to carry out the contextualizaton-related tasks in such a way that the user neither perceives them nor has to do any effort in providing the system with any information that it needs to perform that contextualization). Additionally, we could include a generality aspect to our proposed framework: the main features of the framework should be easy to adopt in any dialogue system, regardless of the solution proposed to manage the dialogue. Once we define the theoretical basis of our contextualization framework, we propose two cases of study on its application in a spoken dialogue system. We focus on two aspects of the interaction: the contextualization of the speech recognition models, and the incorporation of user-specific information into the dialogue flow. One of the modules of a dialogue system that is more prone to be contextualized is the speech recognition system. This module makes use of several models to emit a recognition hypothesis from the user’s speech signal. Generally speaking, a recognition system considers two types of models: an acoustic one (that models each of the phonemes that the recognition system has to consider) and a linguistic one (that models the sequences of words that make sense for the system). In this work we contextualize the language model of the recognition system in such a way that it takes into account the information provided by the user in both his or her current utterance and in the previous ones. These utterances convey information useful to help the system in the recognition of the next utterance. The contextualization approach that we propose consists of a dynamic adaptation of the language model that is used by the recognition system. We carry out this adaptation by means of a linear interpolation between several models. Instead of training the best interpolation weights, we make them dependent on the conditions of the dialogue. In our approach, the system itself will obtain these weights as a function of the reliability of the different elements of information available, such as the semantic concepts extracted from the user’s utterance, the actions that he or she wants to carry out, the information provided in the previous interactions, and so on. One of the aspects more frequently addressed in Human-Computer Interaction research is the inclusion of user specific characteristics into the information structures managed by the system. The idea is to take into account the features that make each user different from the others in order to offer to each particular user different services (or the same service, but in a different way). We could consider this approach as a user-dependent contextualization of the system. In our work we propose the definition of a user model that contains all the information of each user that could be potentially useful to the system at a given moment of the interaction. In particular we will analyze the actions that each user carries out throughout his or her interaction. The objective is to determine which of these actions become the preferences of that user. We represent the specific information of each user as a feature vector. Each of the characteristics that the system will take into account has a confidence score associated. With these elements, we propose a probabilistic definition of a user preference, as the action whose likelihood of being addressed by the user is greater than the one for the rest of actions. To include the user dependent information into the dialogue flow, we modify the information structures on which the dialogue manager relies to retrieve information that could be needed to solve the actions addressed by the user. Usage preferences become another source of contextual information that will be considered by the system towards a more efficient interaction (since the new information source will help to decrease the need of the system to ask users for additional information, thus reducing the number of turns needed to carry out a specific action). To test the benefits of the contextualization framework that we propose, we carry out an evaluation of the two strategies aforementioned. We gather several performance metrics, both objective and subjective, that allow us to compare the improvements of a contextualized system against the baseline one. We will also gather the user’s opinions as regards their perceptions on the behaviour of the system, and its degree of adaptation to the specific features of each interaction. Resumen El diseño y el desarrollo de sistemas de interacción hablada ha sido objeto de profundo estudio durante las pasadas décadas. El propósito es la consecución de sistemas con la capacidad de interactuar con agentes humanos con un alto grado de eficiencia y naturalidad. De esta manera, los usuarios pueden desempeñar las tareas que deseen empleando la voz, que es el medio de comunicación más natural para los humanos. A fin de alcanzar el grado de naturalidad deseado, no basta con dotar a los sistemas de la abilidad de comprender las intervenciones de los usuarios y reaccionar a ellas de manera apropiada (teniendo en consideración, incluso, la información proporcionada en previas interacciones). Adicionalmente, el sistema ha de ser consciente de las condiciones bajo las cuales transcurre la interacción, así como de la evolución de las mismas, de tal manera que pueda actuar de la manera más coherente en cada instante de la interacción. En consecuencia, una de las características primordiales del sistema es que debe ser sensible al contexto. Esta capacidad del sistema de conocer y emplear el contexto de la interacción puede verse reflejada en la modificación de su comportamiento debida a las características actuales de la interacción. Por ejemplo, el sistema debería decidir cuál es la acción más apropiada, o la mejor manera de llevarla a término, dependiendo del usuario que la solicita, del modo en el que lo hace, etcétera. En otras palabras, el sistema ha de adaptar su comportamiento a tales elementos mutables (o dinámicos) de la interacción. Dos características adicionales son requeridas a dicha adaptación: i) el usuario no ha de percibir que el sistema dedica recursos (temporales o computacionales) a realizar tareas distintas a las que aquél le solicita, y ii) el usuario no ha de dedicar esfuerzo alguno a proporcionar al sistema información adicional para llevar a cabo la interacción. Esto último implicaría una menor eficiencia de la interacción, puesto que los usuarios deberían dedicar parte de la misma a proporcionar información al sistema para su adaptación, sin ningún beneficio inmediato. En los sistemas de diálogo hablado propuestos en la literatura, se han propuesto diferentes estrategias para llevar a cabo la adaptación de los elementos del sistema a las diferentes condiciones de la interacción (tales como las características acústicas del habla de un usuario particular, o a las acciones a las que se ha referido con anterioridad). Sin embargo, no existe una estrategia fija para proceder a dicha adaptación, sino que las mismas no suelen guardar una relación entre sí. En este sentido, cada una de ellas tiene en cuenta distintas fuentes de información, la cual es tratada de manera diferente en función de las características de la adaptación buscada. Teniendo en cuenta lo anterior, las contribuciones principales de esta Tesis son las siguientes: Definición de un marco de contextualización. Proponemos un criterio unificador que pueda cubrir cualquier estrategia de adaptación del comportamiento de un sistema de diálogo a las condiciones de la interacción (esto es, el contexto de la misma). En nuestra definición teórica del marco de contextualización consideramos el contexto del sistema como todas aquellas fuentes de variabilidad presentes en cualquier instante de la interacción, ya estén relacionadas con el entorno en el que tiene lugar la interacción, ya dependan del agente humano que se dirige al sistema en cada momento. Nuestra propuesta se basa en tres aspectos que cualquier estrategia de contextualización debería cumplir: plasticidad (es decir, el sistema ha de ser capaz de modificar su comportamiento de la manera más proactiva posible, teniendo en cuenta las condiciones en las que tiene lugar la interacción), adaptabilidad (esto es, el sistema ha de ser capaz de considerar la información oportuna en cada instante, ya dependa del entorno o del usuario, de tal manera que adecúe su comportamiento de manera eficaz a las condiciones mencionadas), y transparencia (que implica que el sistema ha de desarrollar las tareas relacionadas con la contextualización de tal manera que el usuario no perciba la manera en que dichas tareas se llevan a cabo, ni tampoco deba proporcionar al sistema con información adicional alguna). De manera adicional, incluiremos en el marco propuesto el aspecto de la generalidad: las características del marco de contextualización han de ser portables a cualquier sistema de diálogo, con independencia de la solución propuesta en los mismos para gestionar el diálogo. Una vez hemos definido las características de alto nivel de nuestro marco de contextualización, proponemos dos estrategias de aplicación del mismo a un sistema de diálogo hablado. Nos centraremos en dos aspectos de la interacción a adaptar: los modelos empleados en el reconocimiento de habla, y la incorporación de información específica de cada usuario en el flujo de diálogo. Uno de los módulos de un sistema de diálogo más susceptible de ser contextualizado es el sistema de reconocimiento de habla. Este módulo hace uso de varios modelos para generar una hipótesis de reconocimiento a partir de la señal de habla. En general, un sistema de reconocimiento emplea dos tipos de modelos: uno acústico (que modela cada uno de los fonemas considerados por el reconocedor) y uno lingüístico (que modela las secuencias de palabras que tienen sentido desde el punto de vista de la interacción). En este trabajo contextualizamos el modelo lingüístico del reconocedor de habla, de tal manera que tenga en cuenta la información proporcionada por el usuario, tanto en su intervención actual como en las previas. Estas intervenciones contienen información (semántica y/o discursiva) que puede contribuir a un mejor reconocimiento de las subsiguientes intervenciones del usuario. La estrategia de contextualización propuesta consiste en una adaptación dinámica del modelo de lenguaje empleado en el reconocedor de habla. Dicha adaptación se lleva a cabo mediante una interpolación lineal entre diferentes modelos. En lugar de entrenar los mejores pesos de interpolación, proponemos hacer los mismos dependientes de las condiciones actuales de cada diálogo. El propio sistema obtendrá estos pesos como función de la disponibilidad y relevancia de las diferentes fuentes de información disponibles, tales como los conceptos semánticos extraídos a partir de la intervención del usuario, o las acciones que el mismo desea ejecutar. Uno de los aspectos más comúnmente analizados en la investigación de la Interacción Persona-Máquina es la inclusión de las características específicas de cada usuario en las estructuras de información empleadas por el sistema. El objetivo es tener en cuenta los aspectos que diferencian a cada usuario, de tal manera que el sistema pueda ofrecer a cada uno de ellos el servicio más apropiado (o un mismo servicio, pero de la manera más adecuada a cada usuario). Podemos considerar esta estrategia como una contextualización dependiente del usuario. En este trabajo proponemos la definición de un modelo de usuario que contenga toda la información relativa a cada usuario, que pueda ser potencialmente utilizada por el sistema en un momento determinado de la interacción. En particular, analizaremos aquellas acciones que cada usuario decide ejecutar a lo largo de sus diálogos con el sistema. Nuestro objetivo es determinar cuáles de dichas acciones se convierten en las preferencias de cada usuario. La información de cada usuario quedará representada mediante un vector de características, cada una de las cuales tendrá asociado un valor de confianza. Con ambos elementos proponemos una definición probabilística de una preferencia de uso, como aquella acción cuya verosimilitud es mayor que la del resto de acciones solicitadas por el usuario. A fin de incluir la información dependiente de usuario en el flujo de diálogo, llevamos a cabo una modificación de las estructuras de información en las que se apoya el gestor de diálogo para recuperar información necesaria para resolver ciertos diálogos. En dicha modificación las preferencias de cada usuario pasarán a ser una fuente adicional de información contextual, que será tenida en cuenta por el sistema en aras de una interacción más eficiente (puesto que la nueva fuente de información contribuirá a reducir la necesidad del sistema de solicitar al usuario información adicional, dando lugar en consecuencia a una reducción del número de intervenciones necesarias para llevar a cabo una acción determinada). Para determinar los beneficios de las aplicaciones del marco de contextualización propuesto, llevamos a cabo una evaluación de un sistema de diálogo que incluye las estrategias mencionadas. Hemos recogido diversas métricas, tanto objetivas como subjetivas, que nos permiten determinar las mejoras aportadas por un sistema contextualizado en comparación con el sistema sin contextualizar. De igual manera, hemos recogido las opiniones de los participantes en la evaluación acerca de su percepción del comportamiento del sistema, y de su capacidad de adaptación a las condiciones concretas de cada interacción.
Resumo:
Sensor networks are increasingly being deployed in the environment for many different purposes. The observations that they produce are made available with heterogeneous schemas, vocabularies and data formats, making it difficult to share and reuse this data, for other purposes than those for which they were originally set up. The authors propose an ontology-based approach for providing data access and query capabilities to streaming data sources, allowing users to express their needs at a conceptual level, independent of implementation and language-specific details. In this article, the authors describe the theoretical foundations and technologies that enable exposing semantically enriched sensor metadata, and querying sensor observations through SPARQL extensions, using query rewriting and data translation techniques according to mapping languages, and managing both pull and push delivery modes.
