SemQuaRE - An extension of the SQuaRE quality model for the evaluation of semantic technologies

To correctly evaluate semantic technologies and to obtain results that can be easily integrated, we need to put evaluations under the scope of a unique software quality model. This paper presents SemQuaRE, a quality model for semantic technologies. SemQuaRE is based on the SQuaRE standard and describes a set of quality characteristics specific to semantic technologies and the quality measures that can be used for their measurement. It also provides detailed formulas for the calculation of such measures. The paper shows that SemQuaRE is complete with respect to current evaluation trends and that it has been successfully applied in practice.

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.

Using WYSIWYM to Create an Open-ended Interface for the Semantic Grid

Publisher PDF

A Semantic Workflow Mechanism to Realize Experimental Goals and Constraints

Postprint

Semantic Support for Computational Land-Use Modelling

Postprint

Cultural universals: Measuring the semantic structure of emotion terms in English and Japanese

Research is presented on the semantic structure of 15 emotion terms as measured by judged-similarity tasks for monolingual English-speaking and monolingual and bilingual Japanese subjects. A major question is the relative explanatory power of a single shared model for English and Japanese versus culture-specific models for each language. The data support a shared model for the semantic structure of emotion terms even though some robust and significant differences are found between English and Japanese structures. The Japanese bilingual subjects use a model more like English when performing tasks in English than when performing the same task in Japanese.

Role of left inferior prefrontal cortex in retrieval of semantic knowledge: A reevaluation

A number of neuroimaging findings have been interpreted as evidence that the left inferior frontal gyrus (IFG) subserves retrieval of semantic knowledge. We provide a fundamentally different interpretation, that it is not retrieval of semantic knowledge per se that is associated with left IFG activity but rather selection of information among competing alternatives from semantic memory. Selection demands were varied across three semantic tasks in a single group of subjects. Functional magnetic resonance imaging signal in overlapping regions of left IFG was dependent on selection demands in all three tasks. In addition, the degree of semantic processing was varied independently of selection demands in one of the tasks. The absence of left IFG activity for this comparison counters the argument that the effects of selection can be attributed solely to variations in degree of semantic retrieval. Our findings suggest that it is selection, not retrieval, of semantic knowledge that drives activity in the left IFG.

Statistical methods for characterizing similarities and differences between semantic structures

This paper describes a variety of statistical methods for obtaining precise quantitative estimates of the similarities and differences in the structures of semantic domains in different languages. The methods include comparing mean correlations within and between groups, principal components analysis of interspeaker correlations, and analysis of variance of speaker by question data. Methods for graphical displays of the results are also presented. The methods give convergent results that are mutually supportive and equivalent under suitable interpretation. The methods are illustrated on the semantic domain of emotion terms in a comparison of the semantic structures of native English and native Japanese speaking subjects. We suggest that, in comparative studies concerning the extent to which semantic structures are universally shared or culture-specific, both similarities and differences should be measured and compared rather than placing total emphasis on one or the other polar position.

Neural basis of lexical-semantic processing and integration of symbolic gestures with words

Three studies investigated the relation between symbolic gestures and words, aiming at discover the neural basis and behavioural features of the lexical semantic processing and integration of the two communicative signals. The first study aimed at determining whether elaboration of communicative signals (symbolic gestures and words) is always accompanied by integration with each other and, if present, this integration can be considered in support of the existence of a same control mechanism. Experiment 1 aimed at determining whether and how gesture is integrated with word. Participants were administered with a semantic priming paradigm with a lexical decision task and pronounced a target word, which was preceded by a meaningful or meaningless prime gesture. When meaningful, the gesture could be either congruent or incongruent with word meaning. Duration of prime presentation (100, 250, 400 ms) randomly varied. Voice spectra, lip kinematics, and time to response were recorded and analyzed. Formant 1 of voice spectra, and mean velocity in lip kinematics increased when the prime was meaningful and congruent with the word, as compared to meaningless gesture. In other words, parameters of voice and movement were magnified by congruence, but this occurred only when prime duration was 250 ms. Time to response to meaningful gesture was shorter in the condition of congruence compared to incongruence. Experiment 2 aimed at determining whether the mechanism of integration of a prime word with a target word is similar to that of a prime gesture with a target word. Formant 1 of the target word increased when word prime was meaningful and congruent, as compared to meaningless congruent prime. Increase was, however, present for whatever prime word duration. In the second study, experiment 3 aimed at determining whether symbolic prime gesture comprehension makes use of motor simulation. Transcranial Magnetic Stimulation was delivered to left primary motor cortex 100, 250, 500 ms after prime gesture presentation. Motor Evoked Potential of First Dorsal Interosseus increased when stimulation occurred 100 ms post-stimulus. Thus, gesture was understood within 100ms and integrated with the target word within 250 ms. Experiment 4 excluded any hand motor simulation in order to comprehend prime word. The effect of the prior presentation of a symbolic gesture on congruent target word processing was investigated in study 3. In experiment 5, symbolic gestures were presented as primes, followed by semantically congruent target word or pseudowords. In this case, lexical-semantic decision was accompanied by a motor simulation at 100ms after the onset of the verbal stimuli. Summing up, the same type of integration with a word was present for both prime gesture and word. It was probably subsequent to understanding of the signal, which used motor simulation for gesture and direct access to semantics for words. However, gesture and words could be understood at the same motor level through simulation if words were preceded by an adequate gestural context. Results are discussed in the prospective of a continuum between transitive actions and emblems, in parallelism with language; the grounded/symbolic content of the different signals evidences relation between sensorimotor and linguistic systems, which could interact at different levels.

Defining and Measuring Metrics for a Multinational Human Resources Department

Successful HR departments should support key business objectives by establishing metrics that determine the effectiveness of their processes. Functions such as recruiting, benefits, and training are processes that should have metrics. Understanding who measures what, when, and how often is the first step in measuring how much it costs to run HR. The next step is determining which processes are most critical, and then determining the metrics that fit the business needs. Slight adjustments will need to be made as business needs change, but the process for measuring outcomes should not change. This paper will focus on multinational corporations that employ at least ten thousand employees and have a ratio of one HR professional to every hundred fulltime equivalents (FTEs).

Enriching the integration of semantic resources based on WordNet

In this paper we present the enrichment of the Integration of Semantic Resources based in WordNet (ISR-WN Enriched). This new proposal improves the previous one where several semantic resources such as SUMO, WordNet Domains and WordNet Affects were related, adding other semantic resources such as Semantic Classes and SentiWordNet. Firstly, the paper describes the architecture of this proposal explaining the particularities of each integrated resource. After that, we analyze some problems related to the mappings of different versions and how we solve them. Moreover, we show the advantages that this kind of tool can provide to different applications of Natural Language Processing. Related to that question, we can demonstrate that the integration of semantic resources allows acquiring a multidimensional vision in the analysis of natural language.

Automatic extraction of syntactic semantic patterns for multilingual resources

In this paper we present an automatic system for the extraction of syntactic semantic patterns applied to the development of multilingual processing tools. In order to achieve optimum methods for the automatic treatment of more than one language, we propose the use of syntactic semantic patterns. These patterns are formed by a verbal head and the main arguments, and they are aligned among languages. In this paper we present an automatic system for the extraction and alignment of syntactic semantic patterns from two manually annotated corpora, and evaluate the main linguistic problems that we must deal with in the alignment process.

A general proposal to multilingual information access based on syntactic-semantic patterns

In the last few years, there has been a wide development in the research on textual information systems. The goal is to improve these systems in order to allow an easy localization, treatment and access to the information stored in digital format (Digital Databases, Documental Databases, and so on). There are lots of applications focused on information access (for example, Web-search systems like Google or Altavista). However, these applications have problems when they must access to cross-language information, or when they need to show information in a language different from the one of the query. This paper explores the use of syntactic-sematic patterns as a method to access to multilingual information, and revise, in the case of Information Retrieval, where it is possible and useful to employ patterns when it comes to the multilingual and interactive aspects. On the one hand, the multilingual aspects that are going to be studied are the ones related to the access to documents in different languages from the one of the query, as well as the automatic translation of the document, i.e. a machine translation system based on patterns. On the other hand, this paper is going to go deep into the interactive aspects related to the reformulation of a query based on the syntactic-semantic pattern of the request.

Using WordNet relations and semantic classes in information retrieval tasks

In this paper we explore the use of semantic classes in an existing information retrieval system in order to improve its results. Thus, we use two different ontologies of semantic classes (WordNet domain and Basic Level Concepts) in order to re-rank the retrieved documents and obtain better recall and precision. Finally, we implement a new method for weighting the expanded terms taking into account the weights of the original query terms and their relations in WordNet with respect to the new ones (which have demonstrated to improve the results). The evaluation of these approaches was carried out in the CLEF Robust-WSD Task, obtaining an improvement of 1.8% in GMAP for the semantic classes approach and 10% in MAP employing the WordNet term weighting approach.