Integrating WordNet and Wiktionary with lemon

Nowadays, there is a significant quantity of linguistic data available on the Web. However, linguistic resources are often published using proprietary formats and, as such, it can be difficult to interface with one another and they end up confined in “data silos”. The creation of web standards for the publishing of data on the Web and projects to create Linked Data have lead to interest in the creation of resources that can be published using Web principles. One of the most important aspects of “Lexical Linked Data” is the sharing of lexica and machine readable dictionaries. It is for this reason, that the lemon format has been proposed, which we briefly describe. We then consider two resources that seem ideal candidates for the Linked Data cloud, namely WordNet 3.0 and Wiktionary, a large document based dictionary. We discuss the challenges of converting both resources to lemon , and in particular for Wiktionary, the challenge of processing the mark-up, and handling inconsistencies and underspecification in the source material. Finally, we turn to the task of creating links between the two resources and present a novel algorithm for linking lexica as lexical Linked Data.

Electrical Power Fluctuations in a Network of DC/AC inverters in a Large PV Plant: relationship between correlation, distance and time scale

This paper analyzes the correlation between the fluctuations of the electrical power generated by the ensemble of 70 DC/AC inverters from a 45.6 MW PV plant. The use of real electrical power time series from a large collection of photovoltaic inverters of a same plant is an impor- tant contribution in the context of models built upon simplified assumptions to overcome the absence of such data. This data set is divided into three different fluctuation categories with a clustering proce- dure which performs correctly with the clearness index and the wavelet variances. Afterwards, the time dependent correlation between the electrical power time series of the inverters is esti- mated with the wavelet transform. The wavelet correlation depends on the distance between the inverters, the wavelet time scales and the daily fluctuation level. Correlation values for time scales below one minute are low without dependence on the daily fluctuation level. For time scales above 20 minutes, positive high correlation values are obtained, and the decay rate with the distance depends on the daily fluctuation level. At intermediate time scales the correlation depends strongly on the daily fluctuation level. The proposed methods have been implemented using free software. Source code is available as supplementary material.

Combined use of gliadins and SSRs to analyse the genetic variability of the Spanish collection of cultivated diploid wheat (Triticum monococcum L. ssp. monococcum)

This work studied the combined use of gliadins and SSRs to analyse inter- and intra-accession variability of the Spanish collection of cultivated einkorn (Triticum monococcum L. ssp. monococcum) maintained at the CRF-INIA. In general, gliadin loci presented higher discrimination power than SSRs, reflecting the high variability of the gliadins. The loci on chromosome 6A were the most polymorphic with similar PIC values for both marker systems, showing that these markers are very useful for genetic variability studies in wheat. The gliadin results indicated that the Spanish einkorn collection possessed high genetic diversity, being the differentiation large between varieties and small within them. Some associations between gliadin alleles and geographical and agro-morphological data were found. Agro-morphological relations were also observed in the clusters of the SSRs dendrogram. A high concordance was found between gliadins and SSRs for genotype identification. In addition, both systems provide complementary information to resolve the different cases of intra-accession variability not detected at the agro-morphological level, and to identify separately all the genotypes analysed. The combined use of both genetic markers is an excellent tool for genetic resource evaluation in addition to agro-morphological evaluation.

Analysis of genetic variability in a sample of the durum wheat (Triticum durum Desf.) Spanish collection based on gliadin markers

In this work gliadin proteins were used to analyse the genetic variability in a sample of the durum wheat Spanish collection conserved at the CRF-INIA. In total 38 different alleles were identified at the loci Gli-A1, Gli-A3, Gli-B5, Gli-B1, Gli-A2 and Gli-B2. All the gliadin loci were polymorphic, possessed large genetic diversity and small and large differentiation within and between varieties, respectively. The Gli-A2 and Gli-B2 loci were the most polymorphic, the most fixed within varieties and the most useful to distinguish among varieties. Alternatively, Gli-B1 locus presented the least genetic variability out of the four main loci Gli-A1, Gli-B1, Gli-A2 and Gli-B2. The Gli-B1 alleles coding for the gliadin γ-45, associated with good quality, had an accumulated frequency of 69.7%, showing that the Spanish germplasm could be a good source for breeding quality. The Spanish landraces studied showed new gliadin alleles not catalogued so far. These new alleles might be associated with specific Spanish environment factors. The large number of new alleles identified also indicates that durum wheat Spanish germplasm is rather unique.

Turbulence models of gravitational clustering.

Large-scale structure formation can be modeled as a nonlinear process that transfers energy from the largest scales to successively smaller scales until it is dissipated, in analogy with Kolmogorov’s cascade model of incompressible turbulence. However, cosmic turbulence is very compressible, and vorticity plays a secondary role in it. The simplest model of cosmic turbulence is the adhesion model, which can be studied perturbatively or adapting to it Kolmogorov’s non-perturbative approach to incompressible turbulence. This approach leads to observationally testable predictions, e.g., to the power-law exponent of the matter density two-point correlation function.

Two way clustering of Microarray Data using a Hybrid Approach

The Microarray technique is rather powerful, as it allows to test up thousands of genes at a time, but this produces an overwhelming set of data files containing huge amounts of data, which is quite difficult to pre-process, separate, classify and correlate for interesting conclusions to be extracted. Modern machine learning, data mining and clustering techniques based on information theory, are needed to read and interpret the information contents buried in those large data sets. Independent Component Analysis method can be used to correct the data affected by corruption processes or to filter the uncorrectable one and then clustering methods can group similar genes or classify samples. In this paper a hybrid approach is used to obtain a two way unsupervised clustering for a corrected microarray data.

Semi-supervised subspace clustering and applications to neuroscience

Machine learning techniques are used for extracting valuable knowledge from data. Nowa¬days, these techniques are becoming even more important due to the evolution in data ac¬quisition and storage, which is leading to data with different characteristics that must be exploited. Therefore, advances in data collection must be accompanied with advances in machine learning techniques to solve new challenges that might arise, on both academic and real applications. There are several machine learning techniques depending on both data characteristics and purpose. Unsupervised classification or clustering is one of the most known techniques when data lack of supervision (unlabeled data) and the aim is to discover data groups (clusters) according to their similarity. On the other hand, supervised classification needs data with supervision (labeled data) and its aim is to make predictions about labels of new data. The presence of data labels is a very important characteristic that guides not only the learning task but also other related tasks such as validation. When only some of the available data are labeled whereas the others remain unlabeled (partially labeled data), neither clustering nor supervised classification can be used. This scenario, which is becoming common nowadays because of labeling process ignorance or cost, is tackled with semi-supervised learning techniques. This thesis focuses on the branch of semi-supervised learning closest to clustering, i.e., to discover clusters using available labels as support to guide and improve the clustering process. Another important data characteristic, different from the presence of data labels, is the relevance or not of data features. Data are characterized by features, but it is possible that not all of them are relevant, or equally relevant, for the learning process. A recent clustering tendency, related to data relevance and called subspace clustering, claims that different clusters might be described by different feature subsets. This differs from traditional solutions to data relevance problem, where a single feature subset (usually the complete set of original features) is found and used to perform the clustering process. The proximity of this work to clustering leads to the first goal of this thesis. As commented above, clustering validation is a difficult task due to the absence of data labels. Although there are many indices that can be used to assess the quality of clustering solutions, these validations depend on clustering algorithms and data characteristics. Hence, in the first goal three known clustering algorithms are used to cluster data with outliers and noise, to critically study how some of the most known validation indices behave. The main goal of this work is however to combine semi-supervised clustering with subspace clustering to obtain clustering solutions that can be correctly validated by using either known indices or expert opinions. Two different algorithms are proposed from different points of view to discover clusters characterized by different subspaces. For the first algorithm, available data labels are used for searching for subspaces firstly, before searching for clusters. This algorithm assigns each instance to only one cluster (hard clustering) and is based on mapping known labels to subspaces using supervised classification techniques. Subspaces are then used to find clusters using traditional clustering techniques. The second algorithm uses available data labels to search for subspaces and clusters at the same time in an iterative process. This algorithm assigns each instance to each cluster based on a membership probability (soft clustering) and is based on integrating known labels and the search for subspaces into a model-based clustering approach. The different proposals are tested using different real and synthetic databases, and comparisons to other methods are also included when appropriate. Finally, as an example of real and current application, different machine learning tech¬niques, including one of the proposals of this work (the most sophisticated one) are applied to a task of one of the most challenging biological problems nowadays, the human brain model¬ing. Specifically, expert neuroscientists do not agree with a neuron classification for the brain cortex, which makes impossible not only any modeling attempt but also the day-to-day work without a common way to name neurons. Therefore, machine learning techniques may help to get an accepted solution to this problem, which can be an important milestone for future research in neuroscience. Resumen Las técnicas de aprendizaje automático se usan para extraer información valiosa de datos. Hoy en día, la importancia de estas técnicas está siendo incluso mayor, debido a que la evolución en la adquisición y almacenamiento de datos está llevando a datos con diferentes características que deben ser explotadas. Por lo tanto, los avances en la recolección de datos deben ir ligados a avances en las técnicas de aprendizaje automático para resolver nuevos retos que pueden aparecer, tanto en aplicaciones académicas como reales. Existen varias técnicas de aprendizaje automático dependiendo de las características de los datos y del propósito. La clasificación no supervisada o clustering es una de las técnicas más conocidas cuando los datos carecen de supervisión (datos sin etiqueta), siendo el objetivo descubrir nuevos grupos (agrupaciones) dependiendo de la similitud de los datos. Por otra parte, la clasificación supervisada necesita datos con supervisión (datos etiquetados) y su objetivo es realizar predicciones sobre las etiquetas de nuevos datos. La presencia de las etiquetas es una característica muy importante que guía no solo el aprendizaje sino también otras tareas relacionadas como la validación. Cuando solo algunos de los datos disponibles están etiquetados, mientras que el resto permanece sin etiqueta (datos parcialmente etiquetados), ni el clustering ni la clasificación supervisada se pueden utilizar. Este escenario, que está llegando a ser común hoy en día debido a la ignorancia o el coste del proceso de etiquetado, es abordado utilizando técnicas de aprendizaje semi-supervisadas. Esta tesis trata la rama del aprendizaje semi-supervisado más cercana al clustering, es decir, descubrir agrupaciones utilizando las etiquetas disponibles como apoyo para guiar y mejorar el proceso de clustering. Otra característica importante de los datos, distinta de la presencia de etiquetas, es la relevancia o no de los atributos de los datos. Los datos se caracterizan por atributos, pero es posible que no todos ellos sean relevantes, o igualmente relevantes, para el proceso de aprendizaje. Una tendencia reciente en clustering, relacionada con la relevancia de los datos y llamada clustering en subespacios, afirma que agrupaciones diferentes pueden estar descritas por subconjuntos de atributos diferentes. Esto difiere de las soluciones tradicionales para el problema de la relevancia de los datos, en las que se busca un único subconjunto de atributos (normalmente el conjunto original de atributos) y se utiliza para realizar el proceso de clustering. La cercanía de este trabajo con el clustering lleva al primer objetivo de la tesis. Como se ha comentado previamente, la validación en clustering es una tarea difícil debido a la ausencia de etiquetas. Aunque existen muchos índices que pueden usarse para evaluar la calidad de las soluciones de clustering, estas validaciones dependen de los algoritmos de clustering utilizados y de las características de los datos. Por lo tanto, en el primer objetivo tres conocidos algoritmos se usan para agrupar datos con valores atípicos y ruido para estudiar de forma crítica cómo se comportan algunos de los índices de validación más conocidos. El objetivo principal de este trabajo sin embargo es combinar clustering semi-supervisado con clustering en subespacios para obtener soluciones de clustering que puedan ser validadas de forma correcta utilizando índices conocidos u opiniones expertas. Se proponen dos algoritmos desde dos puntos de vista diferentes para descubrir agrupaciones caracterizadas por diferentes subespacios. Para el primer algoritmo, las etiquetas disponibles se usan para bus¬car en primer lugar los subespacios antes de buscar las agrupaciones. Este algoritmo asigna cada instancia a un único cluster (hard clustering) y se basa en mapear las etiquetas cono-cidas a subespacios utilizando técnicas de clasificación supervisada. El segundo algoritmo utiliza las etiquetas disponibles para buscar de forma simultánea los subespacios y las agru¬paciones en un proceso iterativo. Este algoritmo asigna cada instancia a cada cluster con una probabilidad de pertenencia (soft clustering) y se basa en integrar las etiquetas conocidas y la búsqueda en subespacios dentro de clustering basado en modelos. Las propuestas son probadas utilizando diferentes bases de datos reales y sintéticas, incluyendo comparaciones con otros métodos cuando resulten apropiadas. Finalmente, a modo de ejemplo de una aplicación real y actual, se aplican diferentes técnicas de aprendizaje automático, incluyendo una de las propuestas de este trabajo (la más sofisticada) a una tarea de uno de los problemas biológicos más desafiantes hoy en día, el modelado del cerebro humano. Específicamente, expertos neurocientíficos no se ponen de acuerdo en una clasificación de neuronas para la corteza cerebral, lo que imposibilita no sólo cualquier intento de modelado sino también el trabajo del día a día al no tener una forma estándar de llamar a las neuronas. Por lo tanto, las técnicas de aprendizaje automático pueden ayudar a conseguir una solución aceptada para este problema, lo cual puede ser un importante hito para investigaciones futuras en neurociencia.

Diversity and Genetic structure of the Spanish collection of durum wheat (Triticum turgidum L) landraces

The objectives of this study were to assess diversity and genetic structure of a collection of Spanish durum wheat (Triticum turgidum L) landraces, using SSRs, DArTs and gliadin-markers, and to correlate the distribution of diversity with geographic and climatic features, as well as agro-morphological traits. A high level of diversity was detected in the genotypes analyzed, which were separated into nine populations with a moderate to great genetic divergence among them. The three subspecies taxa, dicoccon, turgidum and durum, present in the collection, largely determined the clustering of the populations. Genotype variation was lower in dicoccon (one major population) and turgidum (two major populations) than in durum (five major populations). Genetic differentiation by the agro-ecological zone of origin was greater in dicoccon and turgidum than in durum. DArT markers revealed two geographic substructures, east-west for dicoccon and northeast-southwest for turgidum. The ssp. durum had a more complex structure, consisting of seven populations with high intra-population variation. DArT markers allowed the detection of subgroups within some populations, with agro-morphological and gliadin differences, and distinct agro-ecological zones of origin. Two different phylogenetic groups were detected; revealing that some durum populations were more related to ssp. turgidum from northern Spain, while others seem to be more related to durum wheats from North Africa

Drifting plasma collection by a positive biased tether wire in LEO-like plasma conditions: current measurement and plasma diagnostic

BETs is a three-year project financed by the Space Program of the European Commission, aimed at developing an efficient deorbit system that could be carried on board any future satellite launched into Low Earth Orbit (LEO). The operational system involves a conductive tape-tether left bare to establish anodic contact with the ambient plasma as a giant Langmuir probe. As a part of this project, we are carrying out both numerical and experimental approaches to estimate the collected current by the positive part of the tether. This paper deals with experimental measurements performed in the IONospheric Atmosphere Simulator (JONAS) plasma chamber of the Onera-Space Environment Department. The JONAS facility is a 9- m3 vacuum chamber equipped with a plasma source providing drifting plasma simulating LEO conditions in terms of density and temperature. A thin metallic cylinder, simulating the tether, is set inside the chamber and polarized up to 1000 V. The Earth's magnetic field is neutralized inside the chamber. In a first time, tether collected current versus tether polarization is measured for different plasma source energies and densities. In complement, several types of Langmuir probes are used at the same location to allow the extraction of both ion densities and electron parameters by computer modeling (classical Langmuir probe characteristics are not accurate enough in the present situation). These two measurements permit estimation of the discrepancies between the theoretical collection laws, orbital motion limited law in particular, and the experimental data in LEO-like conditions without magnetic fields. In a second time, the spatial variations and the time evolutions of the plasma properties around the tether are investigated. Spherical and emissive Langmuir probes are also used for a more extensive characterization of the plasma in space and time dependent analysis. Results show the ion depletion because of the wake effect and the accumulation of- ions upstream of the tether. In some regimes (at large positive potential), oscillations are observed on the tether collected current and on Langmuir probe collected current in specific sites.

Collection effects on close pararell bare tethers

We review previously published results, and present new results, on the way current to a cylindrical probe drops below the orbital-motion-limited (OML) value for probe cross-sections too large or concave. Results on size and shape effects arise from unrelated behavior in the near and far potential field, and apply to a general cross-section, which can be characterised by radius Req and perimeter peij of equivalent circles. These results are used to discuss collection interference among two or more parallel bare tethers when brought from far away to contact.

Classifying GABAergic interneurons with semi-supervised projected model-based clustering

Objectives: A recently introduced pragmatic scheme promises to be a useful catalog of interneuron names.We sought to automatically classify digitally reconstructed interneuronal morphologies according tothis scheme. Simultaneously, we sought to discover possible subtypes of these types that might emergeduring automatic classification (clustering). We also investigated which morphometric properties weremost relevant for this classification.Materials and methods: A set of 118 digitally reconstructed interneuronal morphologies classified into thecommon basket (CB), horse-tail (HT), large basket (LB), and Martinotti (MA) interneuron types by 42 of theworld?s leading neuroscientists, quantified by five simple morphometric properties of the axon and fourof the dendrites. We labeled each neuron with the type most commonly assigned to it by the experts. Wethen removed this class information for each type separately, and applied semi-supervised clustering tothose cells (keeping the others? cluster membership fixed), to assess separation from other types and lookfor the formation of new groups (subtypes). We performed this same experiment unlabeling the cells oftwo types at a time, and of half the cells of a single type at a time. The clustering model is a finite mixtureof Gaussians which we adapted for the estimation of local (per-cluster) feature relevance. We performedthe described experiments on three different subsets of the data, formed according to how many expertsagreed on type membership: at least 18 experts (the full data set), at least 21 (73 neurons), and at least26 (47 neurons).Results: Interneurons with more reliable type labels were classified more accurately. We classified HTcells with 100% accuracy, MA cells with 73% accuracy, and CB and LB cells with 56% and 58% accuracy,respectively. We identified three subtypes of the MA type, one subtype of CB and LB types each, andno subtypes of HT (it was a single, homogeneous type). We got maximum (adapted) Silhouette widthand ARI values of 1, 0.83, 0.79, and 0.42, when unlabeling the HT, CB, LB, and MA types, respectively,confirming the quality of the formed cluster solutions. The subtypes identified when unlabeling a singletype also emerged when unlabeling two types at a time, confirming their validity. Axonal morphometricproperties were more relevant that dendritic ones, with the axonal polar histogram length in the [pi, 2pi) angle interval being particularly useful.Conclusions: The applied semi-supervised clustering method can accurately discriminate among CB, HT, LB, and MA interneuron types while discovering potential subtypes, and is therefore useful for neuronal classification. The discovery of potential subtypes suggests that some of these types are more heteroge-neous that previously thought. Finally, axonal variables seem to be more relevant than dendritic ones fordistinguishing among the CB, HT, LB, and MA interneuron types.

The TRANSPLANTA collection of Arabidopsis lines: a resource for functional analysis of transcription factors based on their conditional over-expression

Transcription factors (TFs) are key regulators of gene expression in all organisms. In eukaryotes, TFs are often represented by functionally redundant members of large gene families. Overexpression might prove a means to unveil the biological functions of redundant TFs; however, constitutive overexpression of TFs frequently causes severe developmental defects, preventing their functional characterization. Conditional overexpression strategies help to overcome this problem. Here, we report on the TRANSPLANTA collection of Arabidopsis lines, each expressing one of 949 TFs under the control of a β–estradiol-inducible promoter. Thus far, 1636 independent homozygous lines, representing an average of 2.6 lines for every TF, have been produced for the inducible expression of 634 TFs. Along with a GUS-GFP reporter, randomly selected TRANSPLANTA lines were tested and confirmed for conditional transgene expression upon β–estradiol treatment. As a proof of concept for the exploitation of this resource, β–estradiol-induced proliferation of root hairs, dark-induced senescence, anthocyanin accumulation and dwarfism were observed in lines conditionally expressing full-length cDNAs encoding RHD6, WRKY22, MYB123/TT2 and MYB26, respectively, in agreement with previously reported phenotypes conferred by these TFs. Further screening performed with other TRANSPLANTA lines allowed the identification of TFs involved in different plant biological processes, illustrating that the collection is a powerful resource for the functional characterization of TFs. For instance, ANAC058 and a TINY/AP2 TF were identified as modulators of ABA-mediated germination potential, and RAP2.10/DEAR4 was identified as a regulator of cell death in the hypocotyl–root transition zone. Seeds of TRANSPLANTA lines have been deposited at the Nottingham Arabidopsis Stock Centre for further distribution.

Large-scale identification of gibberellin-related transcription factor defines group VII ERFs as functional of DELLA partners

DELLA proteins are the master negative regulators in gibberellin (GA) signaling acting in the nucleus as transcriptional regulators. The current view of DELLA action indicates that their activity relies on the physical interaction with transcription factors (TFs). Therefore, the identification of TFs through which DELLAs regulate GA responses is key to understanding these responses from a mechanistic point of view. Here, we have determined the TF interactome of the Arabidopsis (Arabidopsis thaliana) DELLA protein GIBBERELLIN INSENSITIVE and screened a collection of conditional TF overexpressors in search of those that alter GA sensitivity. As a result, we have found RELATED TO APETALA2.3, an ethylene-induced TF belonging to the group VII ETHYLENE RESPONSE FACTOR of the APETALA2/ethylene responsive element binding protein superfamily, as a DELLA interactor with physiological relevance in the context of apical hook development. The combination of transactivation assays and chromatin immunoprecipitation indicates that the interaction with GIBBERELLIN INSENSITIVE impairs the activity of RELATED TO APETALA2.3 on the target promoters. This mechanism represents a unique node in the cross regulation between the GA and ethylene signaling pathways controlling differential growth during apical hook development.

Fast 2D to 3D conversion using a clustering-based hierarchical search in a machine learning framework

Automatic 2D-to-3D conversion is an important application for filling the gap between the increasing number of 3D displays and the still scant 3D content. However, existing approaches have an excessive computational cost that complicates its practical application. In this paper, a fast automatic 2D-to-3D conversion technique is proposed, which uses a machine learning framework to infer the 3D structure of a query color image from a training database with color and depth images. Assuming that photometrically similar images have analogous 3D structures, a depth map is estimated by searching the most similar color images in the database, and fusing the corresponding depth maps. Large databases are desirable to achieve better results, but the computational cost also increases. A clustering-based hierarchical search using compact SURF descriptors to characterize images is proposed to drastically reduce search times. A significant computational time improvement has been obtained regarding other state-of-the-art approaches, maintaining the quality results.

Contributions to Speech Analytics based on Speech Recognition and Topic Identification

La última década ha sido testigo de importantes avances en el campo de la tecnología de reconocimiento de voz. Los sistemas comerciales existentes actualmente poseen la capacidad de reconocer habla continua de múltiples locutores, consiguiendo valores aceptables de error, y sin la necesidad de realizar procedimientos explícitos de adaptación. A pesar del buen momento que vive esta tecnología, el reconocimiento de voz dista de ser un problema resuelto. La mayoría de estos sistemas de reconocimiento se ajustan a dominios particulares y su eficacia depende de manera significativa, entre otros muchos aspectos, de la similitud que exista entre el modelo de lenguaje utilizado y la tarea específica para la cual se está empleando. Esta dependencia cobra aún más importancia en aquellos escenarios en los cuales las propiedades estadísticas del lenguaje varían a lo largo del tiempo, como por ejemplo, en dominios de aplicación que involucren habla espontánea y múltiples temáticas. En los últimos años se ha evidenciado un constante esfuerzo por mejorar los sistemas de reconocimiento para tales dominios. Esto se ha hecho, entre otros muchos enfoques, a través de técnicas automáticas de adaptación. Estas técnicas son aplicadas a sistemas ya existentes, dado que exportar el sistema a una nueva tarea o dominio puede requerir tiempo a la vez que resultar costoso. Las técnicas de adaptación requieren fuentes adicionales de información, y en este sentido, el lenguaje hablado puede aportar algunas de ellas. El habla no sólo transmite un mensaje, también transmite información acerca del contexto en el cual se desarrolla la comunicación hablada (e.g. acerca del tema sobre el cual se está hablando). Por tanto, cuando nos comunicamos a través del habla, es posible identificar los elementos del lenguaje que caracterizan el contexto, y al mismo tiempo, rastrear los cambios que ocurren en estos elementos a lo largo del tiempo. Esta información podría ser capturada y aprovechada por medio de técnicas de recuperación de información (information retrieval) y de aprendizaje de máquina (machine learning). Esto podría permitirnos, dentro del desarrollo de mejores sistemas automáticos de reconocimiento de voz, mejorar la adaptación de modelos del lenguaje a las condiciones del contexto, y por tanto, robustecer al sistema de reconocimiento en dominios con condiciones variables (tales como variaciones potenciales en el vocabulario, el estilo y la temática). En este sentido, la principal contribución de esta Tesis es la propuesta y evaluación de un marco de contextualización motivado por el análisis temático y basado en la adaptación dinámica y no supervisada de modelos de lenguaje para el robustecimiento de un sistema automático de reconocimiento de voz. Esta adaptación toma como base distintos enfoque de los sistemas mencionados (de recuperación de información y aprendizaje de máquina) mediante los cuales buscamos identificar las temáticas sobre las cuales se está hablando en una grabación de audio. Dicha identificación, por lo tanto, permite realizar una adaptación del modelo de lenguaje de acuerdo a las condiciones del contexto. El marco de contextualización propuesto se puede dividir en dos sistemas principales: un sistema de identificación de temática y un sistema de adaptación dinámica de modelos de lenguaje. Esta Tesis puede describirse en detalle desde la perspectiva de las contribuciones particulares realizadas en cada uno de los campos que componen el marco propuesto: _ En lo referente al sistema de identificación de temática, nos hemos enfocado en aportar mejoras a las técnicas de pre-procesamiento de documentos, asimismo en contribuir a la definición de criterios más robustos para la selección de index-terms. – La eficiencia de los sistemas basados tanto en técnicas de recuperación de información como en técnicas de aprendizaje de máquina, y específicamente de aquellos sistemas que particularizan en la tarea de identificación de temática, depende, en gran medida, de los mecanismos de preprocesamiento que se aplican a los documentos. Entre las múltiples operaciones que hacen parte de un esquema de preprocesamiento, la selección adecuada de los términos de indexado (index-terms) es crucial para establecer relaciones semánticas y conceptuales entre los términos y los documentos. Este proceso también puede verse afectado, o bien por una mala elección de stopwords, o bien por la falta de precisión en la definición de reglas de lematización. En este sentido, en este trabajo comparamos y evaluamos diferentes criterios para el preprocesamiento de los documentos, así como también distintas estrategias para la selección de los index-terms. Esto nos permite no sólo reducir el tamaño de la estructura de indexación, sino también mejorar el proceso de identificación de temática. – Uno de los aspectos más importantes en cuanto al rendimiento de los sistemas de identificación de temática es la asignación de diferentes pesos a los términos de acuerdo a su contribución al contenido del documento. En este trabajo evaluamos y proponemos enfoques alternativos a los esquemas tradicionales de ponderado de términos (tales como tf-idf ) que nos permitan mejorar la especificidad de los términos, así como también discriminar mejor las temáticas de los documentos. _ Respecto a la adaptación dinámica de modelos de lenguaje, hemos dividimos el proceso de contextualización en varios pasos. – Para la generación de modelos de lenguaje basados en temática, proponemos dos tipos de enfoques: un enfoque supervisado y un enfoque no supervisado. En el primero de ellos nos basamos en las etiquetas de temática que originalmente acompañan a los documentos del corpus que empleamos. A partir de estas, agrupamos los documentos que forman parte de la misma temática y generamos modelos de lenguaje a partir de dichos grupos. Sin embargo, uno de los objetivos que se persigue en esta Tesis es evaluar si el uso de estas etiquetas para la generación de modelos es óptimo en términos del rendimiento del reconocedor. Por esta razón, nosotros proponemos un segundo enfoque, un enfoque no supervisado, en el cual el objetivo es agrupar, automáticamente, los documentos en clusters temáticos, basándonos en la similaridad semántica existente entre los documentos. Por medio de enfoques de agrupamiento conseguimos mejorar la cohesión conceptual y semántica en cada uno de los clusters, lo que a su vez nos permitió refinar los modelos de lenguaje basados en temática y mejorar el rendimiento del sistema de reconocimiento. – Desarrollamos diversas estrategias para generar un modelo de lenguaje dependiente del contexto. Nuestro objetivo es que este modelo refleje el contexto semántico del habla, i.e. las temáticas más relevantes que se están discutiendo. Este modelo es generado por medio de la interpolación lineal entre aquellos modelos de lenguaje basados en temática que estén relacionados con las temáticas más relevantes. La estimación de los pesos de interpolación está basada principalmente en el resultado del proceso de identificación de temática. – Finalmente, proponemos una metodología para la adaptación dinámica de un modelo de lenguaje general. El proceso de adaptación tiene en cuenta no sólo al modelo dependiente del contexto sino también a la información entregada por el proceso de identificación de temática. El esquema usado para la adaptación es una interpolación lineal entre el modelo general y el modelo dependiente de contexto. Estudiamos también diferentes enfoques para determinar los pesos de interpolación entre ambos modelos. Una vez definida la base teórica de nuestro marco de contextualización, proponemos su aplicación dentro de un sistema automático de reconocimiento de voz. Para esto, nos enfocamos en dos aspectos: la contextualización de los modelos de lenguaje empleados por el sistema y la incorporación de información semántica en el proceso de adaptación basado en temática. En esta Tesis proponemos un marco experimental basado en una arquitectura de reconocimiento en ‘dos etapas’. En la primera etapa, empleamos sistemas basados en técnicas de recuperación de información y aprendizaje de máquina para identificar las temáticas sobre las cuales se habla en una transcripción de un segmento de audio. Esta transcripción es generada por el sistema de reconocimiento empleando un modelo de lenguaje general. De acuerdo con la relevancia de las temáticas que han sido identificadas, se lleva a cabo la adaptación dinámica del modelo de lenguaje. En la segunda etapa de la arquitectura de reconocimiento, usamos este modelo adaptado para realizar de nuevo el reconocimiento del segmento de audio. Para determinar los beneficios del marco de trabajo propuesto, llevamos a cabo la evaluación de cada uno de los sistemas principales previamente mencionados. Esta evaluación es realizada sobre discursos en el dominio de la política usando la base de datos EPPS (European Parliamentary Plenary Sessions - Sesiones Plenarias del Parlamento Europeo) del proyecto europeo TC-STAR. Analizamos distintas métricas acerca del rendimiento de los sistemas y evaluamos las mejoras propuestas con respecto a los sistemas de referencia. ABSTRACT The last decade has witnessed major advances in speech recognition technology. Today’s commercial systems are able to recognize continuous speech from numerous speakers, with acceptable levels of error and without the need for an explicit adaptation procedure. Despite this progress, speech recognition is far from being a solved problem. Most of these systems are adjusted to a particular domain and their efficacy depends significantly, among many other aspects, on the similarity between the language model used and the task that is being addressed. This dependence is even more important in scenarios where the statistical properties of the language fluctuates throughout the time, for example, in application domains involving spontaneous and multitopic speech. Over the last years there has been an increasing effort in enhancing the speech recognition systems for such domains. This has been done, among other approaches, by means of techniques of automatic adaptation. These techniques are applied to the existing systems, specially since exporting the system to a new task or domain may be both time-consuming and expensive. Adaptation techniques require additional sources of information, and the spoken language could provide some of them. It must be considered that speech not only conveys a message, it also provides information on the context in which the spoken communication takes place (e.g. on the subject on which it is being talked about). Therefore, when we communicate through speech, it could be feasible to identify the elements of the language that characterize the context, and at the same time, to track the changes that occur in those elements over time. This information can be extracted and exploited through techniques of information retrieval and machine learning. This allows us, within the development of more robust speech recognition systems, to enhance the adaptation of language models to the conditions of the context, thus strengthening the recognition system for domains under changing conditions (such as potential variations in vocabulary, style and topic). In this sense, the main contribution of this Thesis is the proposal and evaluation of a framework of topic-motivated contextualization based on the dynamic and non-supervised adaptation of language models for the enhancement of an automatic speech recognition system. This adaptation is based on an combined approach (from the perspective of both information retrieval and machine learning fields) whereby we identify the topics that are being discussed in an audio recording. The topic identification, therefore, enables the system to perform an adaptation of the language model according to the contextual conditions. The proposed framework can be divided in two major systems: a topic identification system and a dynamic language model adaptation system. This Thesis can be outlined from the perspective of the particular contributions made in each of the fields that composes the proposed framework: _ Regarding the topic identification system, we have focused on the enhancement of the document preprocessing techniques in addition to contributing in the definition of more robust criteria for the selection of index-terms. – Within both information retrieval and machine learning based approaches, the efficiency of topic identification systems, depends, to a large extent, on the mechanisms of preprocessing applied to the documents. Among the many operations that encloses the preprocessing procedures, an adequate selection of index-terms is critical to establish conceptual and semantic relationships between terms and documents. This process might also be weakened by a poor choice of stopwords or lack of precision in defining stemming rules. In this regard we compare and evaluate different criteria for preprocessing the documents, as well as for improving the selection of the index-terms. This allows us to not only reduce the size of the indexing structure but also to strengthen the topic identification process. – One of the most crucial aspects, in relation to the performance of topic identification systems, is to assign different weights to different terms depending on their contribution to the content of the document. In this sense we evaluate and propose alternative approaches to traditional weighting schemes (such as tf-idf ) that allow us to improve the specificity of terms, and to better identify the topics that are related to documents. _ Regarding the dynamic language model adaptation, we divide the contextualization process into different steps. – We propose supervised and unsupervised approaches for the generation of topic-based language models. The first of them is intended to generate topic-based language models by grouping the documents, in the training set, according to the original topic labels of the corpus. Nevertheless, a goal of this Thesis is to evaluate whether or not the use of these labels to generate language models is optimal in terms of recognition accuracy. For this reason, we propose a second approach, an unsupervised one, in which the objective is to group the data in the training set into automatic topic clusters based on the semantic similarity between the documents. By means of clustering approaches we expect to obtain a more cohesive association of the documents that are related by similar concepts, thus improving the coverage of the topic-based language models and enhancing the performance of the recognition system. – We develop various strategies in order to create a context-dependent language model. Our aim is that this model reflects the semantic context of the current utterance, i.e. the most relevant topics that are being discussed. This model is generated by means of a linear interpolation between the topic-based language models related to the most relevant topics. The estimation of the interpolation weights is based mainly on the outcome of the topic identification process. – Finally, we propose a methodology for the dynamic adaptation of a background language model. The adaptation process takes into account the context-dependent model as well as the information provided by the topic identification process. The scheme used for the adaptation is a linear interpolation between the background model and the context-dependent one. We also study different approaches to determine the interpolation weights used in this adaptation scheme. Once we defined the basis of our topic-motivated contextualization framework, we propose its application into an automatic speech recognition system. We focus on two aspects: the contextualization of the language models used by the system, and the incorporation of semantic-related information into a topic-based adaptation process. To achieve this, we propose an experimental framework based in ‘a two stages’ recognition architecture. In the first stage of the architecture, Information Retrieval and Machine Learning techniques are used to identify the topics in a transcription of an audio segment. This transcription is generated by the recognition system using a background language model. According to the confidence on the topics that have been identified, the dynamic language model adaptation is carried out. In the second stage of the recognition architecture, an adapted language model is used to re-decode the utterance. To test the benefits of the proposed framework, we carry out the evaluation of each of the major systems aforementioned. The evaluation is conducted on speeches of political domain using the EPPS (European Parliamentary Plenary Sessions) database from the European TC-STAR project. We analyse several performance metrics that allow us to compare the improvements of the proposed systems against the baseline ones.