Conflict and cognitive control during sentence comprehension: recruitment of a frontal network during the processing of Spanish object-first sentences.

During sentence processing there is a preference to treat the first noun phrase found as the subject and agent, unless marked the other way. This preference would lead to a conflict in thematic role assignment when the syntactic structure conforms to a non-canonical object-before-subject pattern. Left perisylvian and fronto-parietal brain networks have been found to be engaged by increased computational demands during sentence comprehension, while event-reated brain potentials have been used to study the on-line manifestation of these demands. However, evidence regarding the spatiotemporal organization of brain networks in this domain is scarce. In the current study we used Magnetoencephalography to track spatio-temporally brain activity while Spanish speakers were reading subject- and object-first cleft sentences. Both kinds of sentences remained ambiguous between a subject-first or an object-first interpretation up to the appearance of the second argument. Results show the time-modulation of a frontal network at the disambiguation point of object-first sentences. Moreover, the time windows where these effects took place have been previously related to thematic role integration (300–500 ms) and to sentence reanalysis and resolution of conflicts during processing (beyond 500 ms post-stimulus). These results point to frontal cognitive control as a putative key mechanism which may operate when a revision of the sentence structure and meaning is necessary

Automatic Categorization for Improving Spanish into Spanish Sign Language Machine Translation

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.

Automatic Understanding of ATC Speech: Study of Prospectives and Field Experiments for Several Controller Positions

Although there has been a lot of interest in recognizing and understanding air traffic control (ATC) speech, none of the published works have obtained detailed field data results. We have developed a system able to identify the language spoken and recognize and understand sentences in both Spanish and English. We also present field results for several in-tower controller positions. To the best of our knowledge, this is the first time that field ATC speech (not simulated) is captured, processed, and analyzed. The use of stochastic grammars allows variations in the standard phraseology that appear in field data. The robust understanding algorithm developed has 95% concept accuracy from ATC text input. It also allows changes in the presentation order of the concepts and the correction of errors created by the speech recognition engine improving it by 17% and 25%, respectively, absolute in the percentage of fully correctly understood sentences for English and Spanish in relation to the percentages of fully correctly recognized sentences. The analysis of errors due to the spontaneity of the speech and its comparison to read speech is also carried out. A 96% word accuracy for read speech is reduced to 86% word accuracy for field ATC data for Spanish for the "clearances" task confirming that field data is needed to estimate the performance of a system. A literature review and a critical discussion on the possibilities of speech recognition and understanding technology applied to ATC speech are also given.

UPM system for the translation task

This paper describes the UPM system for translation task at the EMNLP 2011 workshop on statistical machine translation (http://www.statmt.org/wmt11/), and it has been used for both directions: Spanish-English and English-Spanish. This system is based on Moses with two new modules for pre and post processing the sentences. The main contribution is the method proposed (based on the similarity with the source language test set) for selecting the sentences for training the models and adjusting the weights. With system, we have obtained a 23.2 BLEU for Spanish-English and 21.7 BLEU for EnglishSpanish

UPM system for WMT 2012

This paper describes the UPM system for the Spanish-English translation task at the NAACL 2012 workshop on statistical machine translation. This system is based on Moses. We have used all available free corpora, cleaning and deleting some repetitions. In this paper, we also propose a technique for selecting the sentences for tuning the system. This technique is based on the similarity with the sentences to translate. With our approach, we improve the BLEU score from 28.37% to 28.57%. And as a result of the WMT12 challenge we have obtained a 31.80% BLEU with the 2012 test set. Finally, we explain different experiments that we have carried out after the competition.

Methodology for developing a Speech into Sign Language Translation System in a New Semantic Domain

This paper proposes a methodology for developing a speech into sign language translation system considering a user-centered strategy. This method-ology consists of four main steps: analysis of technical and user requirements, data collection, technology adaptation to the new domain, and finally, evalua-tion of the system. The two most demanding tasks are the sign generation and the translation rules generation. Many other aspects can be updated automatical-ly from a parallel corpus that includes sentences (in Spanish and LSE: Lengua de Signos Española) related to the application domain. In this paper, we explain how to apply this methodology in order to develop two translation systems in two specific domains: bus transport information and hotel reception.

A Three-Dimensional B.I.E.M. Program

The program PECET (Boundary Element Program in Three-Dimensional Elasticity) is presented in this paper. This program, written in FORTRAN V and implemen ted on a UNIVAC 1100,has more than 10,000 sentences and 96 routines and has a lot of capabilities which will be explained in more detail. The object of the program is the analysis of 3-D piecewise heterogeneous elastic domains, using a subregionalization process and 3-D parabolic isopara, metric boundary elements. The program uses special data base management which will be described below, and the modularity followed to write it gives a great flexibility to the package. The Method of Analysis includes an adaptive integration process, an original treatment of boundary conditions, a complete treatment of body forces, the utilization of a Modified Conjugate Gradient Method of solution and an original process of storage which makes it possible to save a lot of memory.

The Spanish Travel Subjective Lexicon (STSL).

This paper presents a proposal for a recognition model for the appraisal value of sentences. It is based on splitting the text into independent sentences (full stops) and then analysing the appraisal elements contained in each sentence according to the previous value in the appraisal lexicon. In this lexicon, positive words are assigned a positive coefficient (+1) and negative words a negative coefficient (-1). We take into account word such as ?too?, ?little? (when it is not ?a bit?), ?less?, and ?nothing? than can modify the polarity degree of lexical unit when appear in the nearby environment. If any of these elements are present, then the previous coefficient will be multiplied by (-1), that is, they will change their sign. Our results show a nearly theoretical effectiveness of 90%, despite not achieving the recognition (or misrecognition) of implicit elements. These elements represent approximately 4% of the total of sentences analysed for appraisal and include the errors in the recognition of coordinated sentences. On the one hand, we found that 3.6 % of the sentences could not be recognized because they use different connectors than those included in the model; on the other hand, we found that in 8.6% of the sentences despite using some of the described connectors could not be applied the rules we have developed. The percentage relative to the whole group of appraisal sentences in the corpus was approximately of 5%.

Diseño e implementación de un algoritmo para la detección de la negación de textos clínicos en español

Vivimos en una época en la que cada vez existe una mayor cantidad de información. En el dominio de la salud la historia clínica digital ha permitido digitalizar toda la información de los pacientes. Estas historias clínicas digitales contienen una gran cantidad de información valiosa escrita en forma narrativa que sólo podremos extraer recurriendo a técnicas de procesado de lenguaje natural. No obstante, si se quiere realizar búsquedas sobre estos textos es importante analizar que la información relativa a síntomas, enfermedades, tratamientos etc. se puede refererir al propio paciente o a sus antecentes familiares, y que ciertos términos pueden aparecer negados o ser hipotéticos. A pesar de que el español ocupa la segunda posición en el listado de idiomas más hablados con más de 500 millones de hispano hablantes, hasta donde tenemos de detección de la negación, probabilidad e histórico en textos clínicos en español. Por tanto, este Trabajo Fin de Grado presenta una implementación basada en el algoritmo ConText para la detección de la negación, probabilidad e histórico en textos clínicos escritos en español. El algoritmo se ha validado con 454 oraciones que incluían un total de 1897 disparadores obteniendo unos resultado de 83.5 %, 96.1 %, 96.9 %, 99.7% y 93.4% de exactitud con condiciones afirmados, negados, probable, probable negado e histórico respectivamente. ---ABSTRACT---We live in an era in which there is a huge amount of information. In the domain of health, the electronic health record has allowed to digitize all the information of the patients. These electronic health records contain valuable information written in narrative form that can only be extracted using techniques of natural language processing. However, if you want to search on these texts is important to analyze if the relative information about symptoms, diseases, treatments, etc. are referred to the patient or family casework, and that certain terms may appear negated or be hypothesis. Although Spanish is the second spoken language with more than 500 million speakers, there seems to be no method of detection of negation, hypothesis or historical in medical texts written in Spanish. Thus, this bachelor’s final degree presents an implementation based on the ConText algorithm for the detection of negation, hypothesis and historical in medical texts written in Spanish. The algorithm has been validated with 454 sentences that included a total of 1897 triggers getting a result of 83.5 %, 96.1 %, 96.9 %, 99.7% and 93.4% accuracy with affirmed, negated, hypothesis, negated hypothesis and historical respectively.

Construcción automática de grafos RDF a partir de frases en lenguaje natural para la integración de bases de datos heterogéneas

El presente trabajo desarrolla un servicio REST que transforma frases en lenguaje natural a grafos RDF. Los grafos generados son grafos dirigidos, donde los nodos se forman con los sustantivos o adjetivos de las frases, y los arcos se forman con los verbos. Se utiliza dentro del proyecto p-medicine para dar soporte a las siguientes funcionalidades: Búsquedas en lenguaje natural: actualmente la plataforma p-medicine proporciona un interfaz programático para realizar consultas en SPARQL. El servicio desarrollado permitiría generar esas consultas automáticamente a partir de frases en lenguaje natural. Anotaciones de bases de datos mediante lenguaje natural: la plataforma pmedicine incorpora una herramienta, desarrollada por el Grupo de Ingeniería Biomédica de la Universidad Politécnica de Madrid, para la anotación de bases de datos RDF. Estas anotaciones son necesarias para la posterior traducción de las bases de datos a un esquema central. El proceso de anotación requiere que el usuario construya de forma manual las vistas RDF que desea anotar, lo que requiere mostrar gráficamente el esquema RDF y que el usuario construya vistas RDF seleccionando las clases y relaciones necesarias. Este proceso es a menudo complejo y demasiado difícil para un usuario sin perfil técnico. El sistema se incorporará para permitir que la construcción de estas vistas se realice con lenguaje natural. ---ABSTRACT---The present work develops a REST service that transforms natural language sentences to RDF degrees. Generated graphs are directed graphs where nodes are formed with nouns or adjectives of phrases, and the arcs are formed with verbs. Used within the p-medicine project to support the following functionality: Natural language queries: currently the p-medicine platform provides a programmatic interface to query SPARQL. The developed service would automatically generate those queries from natural language sentences. Memos databases using natural language: the p-medicine platform incorporates a tool, developed by the Group of Biomedical Engineering at the Polytechnic University of Madrid, for the annotation of RDF data bases. Such annotations are necessary for the subsequent translation of databases to a central scheme. The annotation process requires the user to manually construct the RDF views that he wants annotate, requiring graphically display the RDF schema and the user to build RDF views by selecting classes and relationships. This process is often complex and too difficult for a user with no technical background. The system is incorporated to allow the construction of these views to be performed with natural language.

Análisis de textos explicativos del significado de datos cuantitativos

En este Trabajo de Fin de Grado se ha realizado el análisis de textos explicativos de datos cuantitativos, con la finalidad de dar a conocer cuáles son las relaciones, basándose en la Teoría de la Estructura Retórica, entre las distintas frases de un texto de más común uso en documentos periodísticos relacionados con el comportamiento humano y el uso que hacen las personas de las redes sociales. Además de ello se han analizado un conjunto de 20 textos (alrededor de 1200 páginas) obteniendo frases típicas relacionadas con el mismo tema, que sirvieron como base para la construcción del modelo compuesto por un total de 101 patrones. En un futuro, este Trabajo puede ser continuado, si así se desea, para lo cual se plantean las siguientes posibilidades:  Ampliar el conjunto de patrones proporcionado.  Construir un Sistema Generador de Textos automáticos basados en los patrones creados.  Ampliar el estudio y extrapolarlo a diversos temas. ---ABSTRACT---In this Final Project has been performed an analysis of quantitative data explanatory texts, in order to make known what are the relationships, based on Rhetorical Structure Theory, between the different sentences of a text of most common use in journalistic texts related to human behavior and the use people make of social networking. Furthermore have been analyzed a set of 20 texts (about 1200 pages) obtaining typical sentences related to the same topic that served as the basis for construction of the model consists of a total of 101 patterns. In the future, this work can be continued, if so desired, for which the following possibilities are raised:  Extend the set of patterns provided.  Build an Automatic Text Generator System based on the patterns collected in this study.  Expand the study and extrapolate it to various topics.

Diseño, desarrollo y evaluación de sistemas de traducción automática para reducir las barreras de comunicación de las personas sordas

La principal aportación de esta tesis doctoral ha sido la propuesta y evaluación de un sistema de traducción automática que permite la comunicación entre personas oyentes y sordas. Este sistema está formado a su vez por dos sistemas: un traductor de habla en español a Lengua de Signos Española (LSE) escrita y que posteriormente se representa mediante un agente animado; y un generador de habla en español a partir de una secuencia de signos escritos mediante glosas. El primero de ellos consta de un reconocedor de habla, un módulo de traducción entre lenguas y un agente animado que representa los signos en LSE. El segundo sistema está formado por una interfaz gráfica donde se puede especificar una secuencia de signos mediante glosas (palabras en mayúscula que representan los signos), un módulo de traducción entre lenguas y un conversor texto-habla. Para el desarrollo del sistema de traducción, en primer lugar se ha generado un corpus paralelo de 7696 frases en español con sus correspondientes traducciones a LSE. Estas frases pertenecen a cuatro dominios de aplicación distintos: la renovación del Documento Nacional de Identidad, la renovación del permiso de conducir, un servicio de información de autobuses urbanos y la recepción de un hotel. Además, se ha generado una base de datos con más de 1000 signos almacenados en cuatro sistemas distintos de signo-escritura. En segundo lugar, se ha desarrollado un módulo de traducción automática que integra dos técnicas de traducción con una estructura jerárquica: la primera basada en memoria y la segunda estadística. Además, se ha implementado un módulo de pre-procesamiento de las frases en español que, mediante su incorporación al módulo de traducción estadística, permite mejorar significativamente la tasa de traducción. En esta tesis también se ha mejorado la versión de la interfaz de traducción de LSE a habla. Por un lado, se han incorporado nuevas características que mejoran su usabilidad y, por otro, se ha integrado un traductor de lenguaje SMS (Short Message Service – Servicio de Mensajes Cortos) a español, que permite especificar la secuencia a traducir en lenguaje SMS, además de mediante una secuencia de glosas. El sistema de traducción propuesto se ha evaluado con usuarios reales en dos dominios de aplicación: un servicio de información de autobuses de la Empresa Municipal de Transportes de Madrid y la recepción del Hotel Intur Palacio San Martín de Madrid. En la evaluación estuvieron implicadas personas sordas y empleados de los dos servicios. Se extrajeron medidas objetivas (obtenidas por el sistema automáticamente) y subjetivas (mediante cuestionarios a los usuarios). Los resultados fueron muy positivos gracias a la opinión de los usuarios de la evaluación, que validaron el funcionamiento del sistema de traducción y dieron información valiosa para futuras líneas de trabajo. Por otro lado, tras la integración de cada uno de los módulos de los dos sistemas de traducción (habla-LSE y LSE-habla), los resultados de la evaluación y la experiencia adquirida en todo el proceso, una aportación importante de esta tesis doctoral es la propuesta de metodología de desarrollo de sistemas de traducción de habla a lengua de signos en los dos sentidos de la comunicación. En esta metodología se detallan los pasos a seguir para desarrollar el sistema de traducción para un nuevo dominio de aplicación. Además, la metodología describe cómo diseñar cada uno de los módulos del sistema para mejorar su flexibilidad, de manera que resulte más sencillo adaptar el sistema desarrollado a un nuevo dominio de aplicación. Finalmente, en esta tesis se analizan algunas técnicas para seleccionar las frases de un corpus paralelo fuera de dominio para entrenar el modelo de traducción cuando se quieren traducir frases de un nuevo dominio de aplicación; así como técnicas para seleccionar qué frases del nuevo dominio resultan más interesantes que traduzcan los expertos en LSE para entrenar el modelo de traducción. El objetivo es conseguir una buena tasa de traducción con la menor cantidad posible de frases. ABSTRACT The main contribution of this thesis has been the proposal and evaluation of an automatic translation system for improving the communication between hearing and deaf people. This system is made up of two systems: a Spanish into Spanish Sign Language (LSE – Lengua de Signos Española) translator and a Spanish generator from LSE sign sequences. The first one consists of a speech recognizer, a language translation module and an avatar that represents the sign sequence. The second one is made up an interface for specifying the sign sequence, a language translation module and a text-to-speech conversor. For the translation system development, firstly, a parallel corpus has been generated with 7,696 Spanish sentences and their LSE translations. These sentences are related to four different application domains: the renewal of the Identity Document, the renewal of the driver license, a bus information service and a hotel reception. Moreover, a sign database has been generated with more than 1,000 signs described in four different signwriting systems. Secondly, it has been developed an automatic translation module that integrates two translation techniques in a hierarchical structure: the first one is a memory-based technique and the second one is statistical. Furthermore, a pre processing module for the Spanish sentences has been implemented. By incorporating this pre processing module into the statistical translation module, the accuracy of the translation module improves significantly. In this thesis, the LSE into speech translation interface has been improved. On the one hand, new characteristics that improve its usability have been incorporated and, on the other hand, a SMS language into Spanish translator has been integrated, that lets specifying in SMS language the sequence to translate, besides by specifying a sign sequence. The proposed translation system has been evaluated in two application domains: a bus information service of the Empresa Municipal de Transportes of Madrid and the Hotel Intur Palacio San Martín reception. This evaluation has involved both deaf people and services employees. Objective measurements (given automatically by the system) and subjective measurements (given by user questionnaires) were extracted during the evaluation. Results have been very positive, thanks to the user opinions during the evaluation that validated the system performance and gave important information for future work. Finally, after the integration of each module of the two translation systems (speech- LSE and LSE-speech), obtaining the evaluation results and considering the experience throughout the process, a methodology for developing speech into sign language (and vice versa) into a new domain has been proposed in this thesis. This methodology includes the steps to follow for developing the translation system in a new application domain. Moreover, this methodology proposes the way to improve the flexibility of each system module, so that the adaptation of the system to a new application domain can be easier. On the other hand, some techniques are analyzed for selecting the out-of-domain parallel corpus sentences in order to train the translation module in a new domain; as well as techniques for selecting which in-domain sentences are more interesting for translating them (by LSE experts) in order to train the translation model.

Autonomous Acquisition of Natural Situated Communication

An important part of human intelligence, both historically and operationally, is our ability to communicate. We learn how to communicate, and maintain our communicative skills, in a society of communicators – a highly effective way to reach and maintain proficiency in this complex skill. Principles that might allow artificial agents to learn language this way are in completely known at present – the multi-dimensional nature of socio-communicative skills are beyond every machine learning framework so far proposed. Our work begins to address the challenge of proposing a way for observation-based machine learning of natural language and communication. Our framework can learn complex communicative skills with minimal up-front knowledge. The system learns by incrementally producing predictive models of causal relationships in observed data, guided by goal-inference and reasoning using forward-inverse models. We present results from two experiments where our S1 agent learns human communication by observing two humans interacting in a realtime TV-style interview, using multimodal communicative gesture and situated language to talk about recycling of various materials and objects. S1 can learn multimodal complex language and multimodal communicative acts, a vocabulary of 100 words forming natural sentences with relatively complex sentence structure, including manual deictic reference and anaphora. S1 is seeded only with high-level information about goals of the interviewer and interviewee, and a small ontology; no grammar or other information is provided to S1 a priori. The agent learns the pragmatics, semantics, and syntax of complex utterances spoken and gestures from scratch, by observing the humans compare and contrast the cost and pollution related to recycling aluminum cans, glass bottles, newspaper, plastic, and wood. After 20 hours of observation S1 can perform an unscripted TV interview with a human, in the same style, without making mistakes.

Autonomous Acquisition of Natural Language

An important part of human intelligence is the ability to use language. Humans learn how to use language in a society of language users, which is probably the most effective way to learn a language from the ground up. Principles that might allow an artificial agents to learn language this way are not known at present. Here we present a framework which begins to address this challenge. Our auto-catalytic, endogenous, reflective architecture (AERA) supports the creation of agents that can learn natural language by observation. We present results from two experiments where our S1 agent learns human communication by observing two humans interacting in a realtime mock television interview, using gesture and situated language. Results show that S1 can learn multimodal complex language and multimodal communicative acts, using a vocabulary of 100 words with numerous sentence formats, by observing unscripted interaction between the humans, with no grammar being provided to it a priori, and only high-level information about the format of the human interaction in the form of high-level goals of the interviewer and interviewee and a small ontology. The agent learns both the pragmatics, semantics, and syntax of complex sentences spoken by the human subjects on the topic of recycling of objects such as aluminum cans, glass bottles, plastic, and wood, as well as use of manual deictic reference and anaphora.

Methodology for developing an advanced communications system for the Deaf in a new domain

A methodology for developing an advanced communications system for the Deaf in a new domain is presented in this paper. This methodology is a user-centred design approach consisting of four main steps: requirement analysis, parallel corpus generation, technology adaptation to the new domain, and finally, system evaluation. During the requirement analysis, both the user and technical requirements are evaluated and defined. For generating the parallel corpus, it is necessary to collect Spanish sentences in the new domain and translate them into LSE (Lengua de Signos Española: Spanish Sign Language). LSE is represented by glosses and using video recordings. This corpus is used for training the two main modules of the advanced communications system to the new domain: the spoken Spanish into the LSE translation module and the Spanish generation from the LSE module. The main aspects to be generated are the vocabularies for both languages (Spanish words and signs), and the knowledge for translating in both directions. Finally, the field evaluation is carried out with deaf people using the advanced communications system to interact with hearing people in several scenarios. In this evaluation, the paper proposes several objective and subjective measurements for evaluating the performance. In this paper, the new considered domain is about dialogues in a hotel reception. Using this methodology, the system was developed in several months, obtaining very good performance: good translation rates (10% Sign Error Rate) with small processing times, allowing face-to-face dialogues.