La nécessité d'estimer la taille d’un logiciel pour pouvoir en estimer le coût et l’effort nécessaire à son développement est une conséquence de l'utilisation croissante des logiciels dans presque toutes les activités humaines. De plus, la nature compétitive de l’industrie du développement logiciel rend courante l’utilisation d’estimations précises de leur taille, au plus tôt dans le processus de développement. Traditionnellement, l’estimation de la taille des logiciels était accomplie a posteriori à partir de diverses mesures appliquées au code source. Cependant, avec la prise de conscience, par la communauté de l’ingénierie logicielle, que l’estimation de la taille du code est une donnée cruciale pour la maîtrise du développement et des coûts, l’estimation anticipée de la taille des logiciels est devenue une préoccupation répandue. Une fois le code écrit, l’estimation de sa taille et de son coût permettent d'effectuer des études contrastives et éventuellement de contrôler la productivité. D’autre part, les bénéfices apportés par l'estimation de la taille sont d'autant plus grands que cette estimation est effectuée tôt pendant le développement. En outre, si l’estimation de la taille peut être effectuée périodiquement au fur et à mesure de la progression de la conception et du développement, elle peut fournir des informations précieuses aux gestionnaires du projet pour suivre au mieux la progression du développement et affiner en conséquence l'allocation des ressources. Notre recherche se positionne autour des mesures d’estimation de la taille fonctionnelle, couramment appelées Analyse des Points de Fonctions, qui permettent d’estimer la taille d’un logiciel à partir des fonctionnalités qu’il doit fournir à l’utilisateur final, exprimées uniquement selon son point de vue, en excluant en particulier toute considération propre au développement. Un problème significatif de l'utilisation des points de fonction est le besoin d'avoir recours à des experts humains pour effectuer la quotation selon un ensemble de règles de comptage. Le processus d'estimation représente donc une charge de travail conséquente et un coût important. D'autre part, le fait que les règles de comptage des points de fonction impliquent nécessairement une part d'interprétation humaine introduit un facteur d'imprécision dans les estimations et rend plus difficile la reproductibilité des mesures. Actuellement, le processus d'estimation est entièrement manuel et contraint les experts humains à lire en détails l'intégralité des spécifications, une tâche longue et fastidieuse. Nous proposons de fournir aux experts humains une aide automatique dans le processus d'estimation, en identifiant dans le texte des spécifications, les endroits les plus à même de contenir des points de fonction. Cette aide automatique devrait permettre une réduction significative du temps de lecture et de réduire le coût de l'estimation, sans perte de précision. Enfin, l’identification non ambiguë des points de fonction permettra de faciliter et d'améliorer la reproductibilité des mesures. À notre connaissance, les travaux présentés dans cette thèse sont les premiers à se baser uniquement sur l’analyse du contenu textuel des spécifications, applicable dès la mise à disposition des spécifications préliminaires et en se basant sur une approche générique reposant sur des pratiques établies d'analyse automatique du langage naturel. / The inevitable emergence of the necessity to estimate the size of a software thus estimating the probable cost and effort is a direct outcome of increasing need of complex and large software in almost every conceivable situation. Furthermore, due to the competitive nature of the software development industry, the increasing reliance on accurate size estimation at early stages of software development becoming a commonplace practice. Traditionally, estimation of software was performed a posteriori from the resultant source code and several metrics were in practice for the task. However, along with the understanding of the importance of code size estimation in the software engineering community, the realization of early stage software size estimation, became a mainstream concern. Once the code has been written, size and cost estimation primarily provides contrastive study and possibly productivity monitoring. On the other hand, if size estimation can be performed at an early development stage (the earlier the better), the benefits are virtually endless. The most important goals of the financial and management aspect of software development namely development cost and effort estimation can be performed even before the first line of code is being conceived. Furthermore, if size estimation can be performed periodically as the design and development progresses, it can provide valuable information to project managers in terms of progress, resource allocation and expectation management. This research focuses on functional size estimation metrics commonly known as Function Point Analysis (FPA) that estimates the size of a software in terms of the functionalities it is expected to deliver from a user’s point of view. One significant problem with FPA is the requirement of human counters, who need to follow a set of standard counting rules, making the process labour and cost intensive (the process is called Function Point Counting and the professional, either analysts or counters). Moreover, these rules, in many occasion, are open to interpretation, thus they often produce inconsistent counts. Furthermore, the process is entirely manual and requires Function Point (FP) counters to read large specification documents, making it a rather slow process. Some level of automation in the process can make a significant difference in the current counting practice. Automation of the process of identifying the FPs in a document accurately, will at least reduce the reading requirement of the counters, making the process faster and thus shall significantly reduce the cost. Moreover, consistent identification of FPs will allow the production of consistent raw function point counts. To the best of our knowledge, the works presented in this thesis is an unique attempt to analyse specification documents from early stages of the software development, using a generic approach adapted from well established Natural Language Processing (NLP) practices.

A partir do final do século 20, o governo federal criou vários programas visando a ampliação de acesso ao saneamento básico. Embora esses programas tenham trazido o abastecimento de água potável e a coleta de resíduos sólidos para a maioria dos municípios brasileiros, o esgotamento sanitário ainda está espacialmente concentrado na região Sudeste e nas áreas mais urbanizadas. Para explicar esse padrão espacialmente concentrado, é frequentemente assumido que o tamanho das cidades realmente importa para o saneamento básico, especialmente para o esgotamento sanitário. De fato, à medida que as cidades crescem em tamanho, devemos esperar economias de escala no volume de infraestrutura de saneamento. Economias de escala na infra-estrutura implicam uma redução nos custos de saneamento básico, de forma proporcional ao tamanho da cidade, levando também a uma (esperada) relação de lei de escala (ou de potência) entre os gastos com saneamento básico e o tamanho da cidade. Usando a população, N(t), como medida do tamanho da cidade no momento t, a lei de escala para infraestrutura assume o formato Y(t) = Y0N(t)&#946 onde &#946 &#8776 0.8 < 1, Y denota o volume de infraestrutura e Y0 é uma constante. Diversas propriedades das cidades, desde a produção de patentes e renda até a extensão da rede elétrica, são funções de lei de potência do tamanho da população com expoentes de escalamento, &#946, que se enquadram em classes distintas. As quantidades que refletem a criação de riqueza e a inovação têm &#946 &#8776 1.2 > 1 (retornos crescentes), enquanto aquelas responsáveis pela infraestrutura exibem &#946 &#8776 0.8 < 1 (economias de escala). Verificamos essa relação com base em dados extraídos do Sistema Integrado de Planejamento e Orçamento (SIOP), que abrangem transferências com recursos não onerosos, previstos na Lei Orçamentária Anual (LOA), na modalidade saneamento básico. No conjunto, os valores estimados de &#946 mostram redução das transferências da União Federal para saneamento básico, de forma proporcional ao tamanho dos municípios beneficiários. Para a dotação inicial, valores programados na LOA, estimado foi de aproximadamente: 0.63 para municípios com população superior a dois mil habitantes; 0.92 para municípios acima de vinte mil habitantes; e 1.18 para municípios com mais de cinquenta mil habitantes. A segunda fonte de dados identificada foi o Diário Oficial da União (DOU), periódico do governo federal para publicação de atos oficiais. Os dados fornecidos pelo DOU referem-se aos recursos não onerosos e também aos empréstimos com recursos do Fundo de Garantia por Tempo de Serviço (FGTS). Para extração dos dados textuais foram utilizadas técnicas de Processamento de Linguagem Natural(PLN). Essas técnicas funcionam melhor quando os algoritmos são alimentados com anotações - metadados que fornecem informações adicionais sobre o texto. Por isso geramos uma base de dados, a partir de textos anotados do DOU, para treinar uma rede LSTM bidirecional aplicada à etiquetagem morfossintática e ao reconhecimento de entidades nomeadas. Os resultados preliminares obtidos dessa forma estão relatados no texto / Starting in the late 20th century, the Brazilian federal government created several programs to increase the access to water and sanitation. However, although these programs made improvements in water access, sanitation was generally overlooked. While water supply, and waste collection are available in the majority of the Brazilian municipalities, the sewage system is still spatially concentrated in the Southeast region and in the most urbanized areas. In order to explain this spatially concentrated pattern it is frequently assumed that the size of cities does really matter for sanitation services provision, specially for sewage collection. As a matter of fact, as cities grow in size, one should expect economies of scale in sanitation infrastructure volume. Economies of scale in sanitation infrastructure means a decrease in basic sanitation costs, proportional to the city size, leading also to a (expected) power law relationship between the expenditure on sanitation and city size.Using population, N(t), as the measure of city size at time t, power law scaling for infrastructure takes the form Y(t) = Y0N(t)&#946 where &#946 &#8776 0.8 < 1, Y denotes infrastructure volume and is a constant. Many diverse properties of cities from patent production and personal income to electrical cable length are shown to be power law functions of population size with scaling exponents, &#946, that fall into distinct universality classes. Quantities reflecting wealth creation and innovation have &#946 &#8776 1.2 > 1 (increasing returns), whereas those accounting for infrastructure display &#946 &#8776 0.8 < 1 (economies of scale). We verified this relationship using data from federal government databases, called Integrated Planning and Budgeting System, known as SIOP. SIOP data refers only to grants, funds given to municipalities by the federal government to run programs within defined guidelines. Preliminary results from SIOP show decrease in Federal Grants to Brazilian Municipalities, proportional to the city size. For the initial budget allocation, &#946 was found to be roughly 0.63 for municipalities above twenty thousand inhabitants; to be roughly 0.92 for municipalities above twenty thousand inhabitants; and to be roughly 1.18 for municipalities above fifty thousand inhabitants. The second data source is DOU, government journal for publishing official acts. DOU data should give us information not only about grants, but also about FGTS funds for basic sanitation loans. In order to extract data from DOU we have applied Natural Language Processing (NLP) tools. These techniques often work better when the algorithms are provided with annotations metadata that provides additional information about the text. In particular, we fed a database with annotations into a bidirectional LSTM model applied to POS Tagging and Named-entity Recognition. Preliminary results are reported in the paper

Este trabalho apresenta um estudo sobre a utilização de dispositivos adaptativos para realizar tradução texto-voz. O foco do trabalho é a criação de um método para a tradução grafema-fonema para a língua portuguesa baseado em autômatos adaptativos e seu uso em um software de tradução texto-voz. O método apresentado busca mimetizar o comportamento humano no tratamento de regras de tonicidade, separação de sílabas e as influências que as sílabas exercem sobre suas vizinhas. Essa característica torna o método facilmente utilizável para outras variações da língua portuguesa, considerando que essas características são invariantes em relação à localidade e a época da variedade escolhida. A variação contemporânea da língua falada na cidade de São Paulo foi escolhida como alvo de análise e testes neste trabalho. Para essa variação, o modelo apresenta resultados satisfatórios superando 95% de acerto na tradução grafema-fonema de palavras, chegando a 90% de acerto levando em consideração a resolução de dúvidas geradas por palavras que podem possuir duas representações sonoras e gerando uma saída sonora inteligível aos nativos da língua por meio da síntese por concatenação baseada em sílabas. Como resultado do trabalho, além do modelo para tradução grafema-fonema de palavras baseado em autômatos adaptativos, foi criado um método para escolha da representação fonética correta em caso de ambigüidade e foram criados dois softwares, um para simulação de autômatos adaptativos e outro para a tradução grafema-fonema de palavras utilizando o modelo de tradução criado e o método de escolha da representação correta. Esse último software foi unificado ao sintetizador desenvolvido por Koike et al. (2007) para a criação de um tradutor texto-voz para a língua portuguesa. O trabalho mostra a viabilidade da utilização de autômatos adaptativos como base ou como um elemento auxiliar para o processo de tradução texto-voz na língua portuguesa. / This work presents a study on the use of adaptive devices for text-to-speech translation. The work focuses on the development of a grapheme-phoneme translation method for Portuguese based on Adaptive Automata and the use of this method in a text-to-speech translation software. The presented method resembles human behavior when handling syllable separation rules, syllable stress definition and influences syllables have on each other. This feature makes the method easy to use with different variations of Portuguese, since these characteristics are invariants of the language. Portuguese spoken nowadays in São Paulo, Brazil has been chosen as the target for analysis and tests in this work. The method has good results for such variation of Portuguese, reaching 95% accuracy rate for grapheme-phoneme translation, clearing the 90% mark after resolution of ambiguous cases in which different representations are accepted for a grapheme and generating phonetic output intelligible for native speakers based on concatenation synthesis using syllables as concatenation units. As final results of this work, a model is presented for grapheme-phoneme translation for Portuguese words based on Adaptive Automata, a methodology to choose the correct phonetic representation for the grapheme in ambiguous cases, a software for Adaptive Automata simulation and a software for grapheme-phoneme translation of texts using both the model of translation and methodology for disambiguation. The latter software was unified with the speech synthesizer developed by Koike et al. (2007) to create a text-to-speech translator for Portuguese. This work evidences the feasibility of text-to-speech translation for Portuguese using Adaptive Automata as the main instrument for such task.

Esta pesquisa aborda o tema da Elaboração Textual para um público alvo que tem letramento nos níveis básicos e rudimentar, de acordo com a classificação do Indicador Nacional de Alfabetismo Funcional (INAF, 2009). A Elaboração Textual é definida como um conjunto de técnicas que acrescentam material redundante em textos, sendo tradicionalmente usadas a adição de definições, sinônimos, antônimos, ou qualquer informação externa com o objetivo de auxiliar na compreensão do texto. O objetivo deste projeto de mestrado foi a proposta de dois métodos originais de elaboração textual: (1) via definição das entidades mencionadas que aparecem em um texto e (2) via definições de perguntas elaboradas direcionadas aos verbos das orações de um texto. Para a primeira tarefa, usou-se um sistema de reconhecimento de entidades mencionadas da literatura, o Rembrandt, e definições curtas da enciclopédia Wikipédia, sendo este método incorporado no sistema Web FACILITA EDUCATIVO, uma das ferramentas desenvolvidas no projeto PorSimples. O método foi avaliado de forma preliminar com um pequeno grupo de leitores com baixo nível de letramento e a avaliação foi positiva, indicando que este auxílio facilitou a leitura dos usuários da avaliação. O método de geração de perguntas elaboradas aos verbos de uma oração é uma tarefa nova que foi definida, estudada, implementada e avaliada neste mestrado. A avaliação não foi realizada junto ao público alvo e sim com especialistas em processamento de língua natural que avaliaram positivamente o método e indicaram quais erros influenciam negativamente na qualidade das perguntas geradas automaticamente. Existem boas indicações de que os métodos de elaboração desenvolvidos podem ser úteis na melhoria da compreensão da leitura para o público alvo em questão, as pessoas com baixo nível de letramento / This research addresses the topic of Textual Elaboration for low-literacy readers, i.e. people at the rudimentary and basic literacy levels according to the National Indicator of Functional Literacy (INAF, 2009). Text Elaboration consists of a set of techniques that adds extra material in texts using, traditionally, definitions, synonyms, antonyms, or any external information to assist in text understanding. The main goal of this research was the proposal of two methods of Textual Elaboration: (1) the use of short definitions for Named Entities in texts and (2) assignment of wh-questions related to verbs in text. The first task used the Rembrandt named entity recognition system and short definitions of Wikipedia. It was implemented in PorSimples web Educational Facilita tool. This method was preliminarily evaluated with a small group of low-literacy readers. The evaluation results were positive, what indicates that the tool was useful for improving the text understanding. The assignment of wh-questions related to verbs task was defined, studied, implemented and assessed during this research. Its evaluation was conducted with NLP researches instead of with low-literacy readers. There are good evidences that the text elaboration methods and resources developed here are useful in helping text understanding for low-literacy readers

Apesar dos processos de recuperação e filtragem de informação sempre terem usado técnicas básicas de Processamento de Linguagem Natural (PLN) no suporte à estruturação de documentos, ainda são poucas as indicações sobre os avanços relacionados à utilização de técnicas mais sofisticadas de PLN que justifiquem o custo de sua utilização nestes processos, em comparação com as abordagens tradicionais. Este trabalho investiga algumas evidências que fundamentam a hipótese de que a aplicação de métodos que utilizam conhecimento linguístico é viável, demarcando importantes contribuições para o aumento de sua eficiência em adição aos métodos estatásticos tradicionais. É proposto um modelo de representação de texto fundamentado em sintagmas nominais, cuja representatividade de seus descritores é calculada utilizando-se o conceito de evidência, apoiado em métodos estatísticos. Filtros induzidos a partir desse modelo são utilizados para classificar os documentos recuperados analisando-se a relevância implícita no perfil do usuário. O aumento da precisão (e, portanto, da eficácia) em sistemas de Recuperação de Informação, conseqüência da pós-filtragem seletiva de informações, demonstra uma clara evidência de como o uso de técnicas de PLN pode auxiliar a categorização de textos, abrindo reais possibilidades para o aprimoramento do modelo apresentado / Although Information Retrieval and Filtering tasks have always used basic Natural Language Processing (NLP) techniques for supporting document structuring, there is still space for more sophisticated NLP techniques which justify their cost when compared to the traditional approaches. This research aims to investigate some evidences that justify the hypothesis on which the use of linguistic-based methods is feasible and can bring on relevant contributions to this area. In this work noun phrases of a text are used as descriptors whose evidence is calculated by statistical methods. Filters are then induced to classify the retrieved documents by measuring their implicit relevance presupposed by an user profile. The increase of precision (efficacy) in IR systems as a consequence of the use of NLP techniques for text classification in the filtering task is an evidence of how this approach can be further explored

Das Lernen aus strukturierten Eingabe- und Ausgabebeispielen ist die Grundlage für die automatisierte Verarbeitung natürlich auftretender Problemstellungen und eine Herausforderung für das Maschinelle Lernen. Die Einordnung von Objekten in eine Klassentaxonomie, die Eigennamenerkennung und das Parsen natürlicher Sprache sind mögliche Anwendungen. Klassische Verfahren scheitern an der komplexen Natur der Daten, da sie die multiplen Abhängigkeiten und Strukturen nicht erfassen können. Zudem ist die Erhebung von klassifizierten Beispielen in strukturierten Anwendungsgebieten aufwändig und ressourcenintensiv, während unklassifizierte Beispiele günstig und frei verfügbar sind. Diese Arbeit thematisiert halbüberwachte, diskriminative Vorhersagemodelle für strukturierte Daten. Ausgehend von klassischen halbüberwachten Verfahren werden die zugrundeliegenden analytischen Techniken und Algorithmen auf das Lernen mit strukturierten Variablen übertragen. Die untersuchten Verfahren basieren auf unterschiedlichen Prinzipien und Annahmen, wie zum Beispiel der Konsensmaximierung mehrerer Hypothesen im Lernen aus mehreren Sichten, oder der räumlichen Struktur der Daten im transduktiven Lernen. Desweiteren wird in einer Fallstudie zur Email-Batcherkennung die räumliche Struktur der Daten ausgenutzt und eine Lösung präsentiert, die der sequenziellen Natur der Daten gerecht wird. Aus den theoretischen Überlegungen werden halbüberwachte, strukturierte Vorhersagemodelle und effiziente Optmierungsstrategien abgeleitet. Die empirische Evaluierung umfasst Klassifikationsprobleme, Eigennamenerkennung und das Parsen natürlicher Sprache. Es zeigt sich, dass die halbüberwachten Methoden in vielen Anwendungen zu signifikant kleineren Fehlerraten führen als vollständig überwachte Baselineverfahren. / Learning mappings between arbitrary structured input and output variables is a fundamental problem in machine learning. It covers many natural learning tasks and challenges the standard model of learning a mapping from independently drawn instances to a small set of labels. Potential applications include classification with a class taxonomy, named entity recognition, and natural language parsing. In these structured domains, labeled training instances are generally expensive to obtain while unlabeled inputs are readily available and inexpensive. This thesis deals with semi-supervised learning of discriminative models for structured output variables. The analytical techniques and algorithms of classical semi-supervised learning are lifted to the structured setting. Several approaches based on different assumptions of the data are presented. Co-learning, for instance, maximizes the agreement among multiple hypotheses while transductive approaches rely on an implicit cluster assumption. Furthermore, in the framework of this dissertation, a case study on email batch detection in message streams is presented. The involved tasks exhibit an inherent cluster structure and the presented solution exploits the streaming nature of the data. The different approaches are developed into semi-supervised structured prediction models and efficient optimization strategies thereof are presented. The novel algorithms generalize state-of-the-art approaches in structural learning such as structural support vector machines. Empirical results show that the semi-supervised algorithms lead to significantly lower error rates than their fully supervised counterparts in many application areas, including multi-class classification, named entity recognition, and natural language parsing.

Cette thèse présente une modélisation des principaux aspects syntaxiques de la coordination dans les grammaires d'interaction de Guy Perrier. Les grammaires d'interaction permettent d'expliciter la valence des groupes conjoints. C'est précisément sur cette notion qu'est fondée notre modélisation. Nous présentons également tous les travaux autour de cette modélisation qui nous ont permis d'aboutir à une implantation réaliste: le développement du logiciel XMG et son utilisation pour l'écriture de grammaires lexicalisées, le filtrage lexical par intersection d'automates et l'analyse syntaxique. / This thesis presents a modelisation of the main syntactical aspects of coordination using Guy Perrier's Interaction Grammars as the target formalism. Interaction Grammars make it possible to explicitly define conjuncts' valencies. This is precisely what our modelisation is based upon. We also present work around this modelisation that enabled us to provide a realistic implementation: lexicalized grammar development (using our tool XMG), lexical disambiguation based on automata intersection and parsing.

Cette thèse s'intéresse à la modélisation de la syntaxe et de l'interface syntaxe-sémantique de la phrase, et explore la possibilité de contrôler au niveau des structures de dérivation la surgénération que produit le traitement des dépendances à distance par des types d'ordre supérieur. À cet effet, nous étudions la possibilité d'étendre le système de typage des Grammaires Catégorielles Abstraites avec les constructions de la somme disjointe, du produit cartésien et du produit dépendant, permettant d'étiqueter les catégories syntaxiques par des structures de traits. Nous prouvons dans un premier temps que le calcul résultant de cette extension bénéficie des propriétés de confluence et de normalisation, permettant d'identifier les termes beta-équivalents dans le formalisme grammatical. Nous réduisons de plus le même problème pour la beta-eta-équivalence à un ensemble d'hypothèse de départ. Dans un second temps, nous montrons comment cette introduction de structures de traits peut être appliquée au contrôle des dépendances à distances, à travers les exemples des contraintes de cas, des îlots d'extraction pour les mouvements explicites et implicites, et des extractions interrogatives multiples, et nous discutons de la pertinence de placer ces contrôles sur les structures de dérivation / This thesis focuses on the modelisation of syntax and syntax-semantics interface of sentences, and investigate how the control of the surgeneration caused by the treatment of linguistics movements with higher order types can take place at the level of derivation structures. For this purpose, we look at the possibility to extend the type system of Abstract Categorial Grammars with the constructions of disjoint sum, cartesian product and dependent product, which enable syntactic categories to be labeled by feature structures. At first, we demonstrate that the calculus associated with this extension enjoy the properties of confluence and normalization, by which beta-equivalence can be computed in the grammatical formalism. We also reduce the same problem for beta-eta-equivalence to a few hypothesis. Then, we show how this feature structures can be used to control linguistics movements, through the examples of case constraints, extraction islands for overt and covert movements and multiples interrogative extractions, and we discuss the relevancy of operating these controls on the derivation structures

De par leur grand nombre et leur sévérité, les maladies rares (MR) constituent un enjeu de santé majeur. Des bases de données de référence, comme Orphanet et Orphadata, répertorient les informations disponibles à propos de ces maladies. Cependant, il est difficile pour ces bases de données de proposer un contenu complet et à jour par rapport à ce qui est disponible dans la littérature. En effet, des millions de publications scientifiques sur ces maladies sont disponibles et leur nombre augmente de façon continue. Par conséquent, il serait très fastidieux d’extraire manuellement et de façon exhaustive des informations sur ces maladies. Cela motive le développement des approches semi-automatiques pour extraire l’information des textes et la représenter dans un format approprié pour son utilisation dans d’autres applications. Cette thèse s’intéresse à l’extraction de connaissances à partir de textes et propose d’utiliser les résultats de l’extraction pour enrichir une ontologie de domaine. Nous avons étudié trois directions de recherche: (1) l’extraction de connaissances à partir de textes, et en particulier l’extraction de relations maladie-phénotype (M-P); (2) l’identification d’entité nommées complexes, en particulier de phénotypes de MR; et (3) l’enrichissement d’une ontologie en considérant les connaissances extraites à partir de texte. Tout d’abord, nous avons fouillé une collection de résumés d’articles scientifiques représentés sous la forme graphes pour un extraire des connaissances sur les MR. Nous nous sommes concentrés sur la complétion de la description des MR, en extrayant les relations M-P. Cette trouve des applications dans la mise à jour des bases de données de MR telles que Orphanet. Pour cela, nous avons développé un système appelé SPARE* qui extrait les relations M-P à partir des résumés PubMed, où les phénotypes et les MR sont annotés au préalable par un système de reconnaissance des entités nommées. SPARE* suit une approche hybride qui combine une méthode basée sur des patrons syntaxique, appelée SPARE, et une méthode d’apprentissage automatique (les machines à vecteurs de support ou SVM). SPARE* bénéficié à la fois de la précision relativement bonne de SPARE et du bon rappel des SVM. Ensuite, SPARE* a été utilisé pour identifier des phénotypes candidats à partir de textes. Pour cela, nous avons sélectionné des patrons syntaxiques qui sont spécifiques aux relations M-P uniquement. Ensuite, ces patrons sont relaxés au niveau de leur contrainte sur le phénotype pour permettre l’identification de phénotypes candidats qui peuvent ne pas être références dans les bases de données ou les ontologies. Ces candidats sont vérifiés et validés par une comparaison avec les classes de phénotypes définies dans une ontologie de domaine comme HPO. Cette comparaison repose sur une modèle sémantique et un ensemble de règles de mises en correspondance définies manuellement pour cartographier un phénotype candidate extrait de texte avec une classe de l’ontologie. Nos expériences illustrent la capacité de SPARE* à des phénotypes de MR déjà répertoriés ou complètement inédits. Nous avons appliqué SPARE* à un ensemble de résumés PubMed pour extraire les phénotypes associés à des MR, puis avons mis ces phénotypes en correspondance avec ceux déjà répertoriés dans l’encyclopédie Orphanet et dans Orphadata ; ceci nous a permis d’identifier de nouveaux phénotypes associés à la maladie selon les articles, mais pas encore listés dans Orphanet ou Orphadata.Enfin, nous avons appliqué les structures de patrons pour classer les MR et enrichir une ontologie préexistante. Tout d’abord, nous avons utilisé SPARE* pour compléter les descriptions en terme de phénotypes de MR disponibles dans Orphadata. Ensuite, nous proposons de compter et grouper les MR au regard de leur description phénotypique, et ce en utilisant les structures de patron. [...] / Even if they are uncommon, Rare Diseases (RDs) are numerous and generally sever, what makes their study important from a health-care point of view. Few databases provide information about RDs, such as Orphanet and Orphadata. Despite their laudable effort, they are incomplete and usually not up-to-date in comparison with what exists in the literature. Indeed, there are millions of scientific publications about these diseases, and the number of these publications is increasing in a continuous manner. This makes the manual extraction of this information painful and time consuming and thus motivates the development of semi-automatic approaches to extract information from texts and represent it in a format suitable for further applications. This thesis aims at extracting information from texts and using the result of the extraction to enrich existing ontologies of the considered domain. We studied three research directions (1) extracting relationships from text, i.e., extracting Disease-Phenotype (D-P) relationships; (2) identifying new complex entities, i.e., identifying phenotypes of a RD and (3) enriching an existing ontology on the basis of the relationship previously extracted, i.e., enriching a RD ontology. First, we mined a collection of abstracts of scientific articles that are represented as a collection of graphs for discovering relevant pieces of biomedical knowledge. We focused on the completion of RD description, by extracting D-P relationships. This could find applications in automating the update process of RD databases such as Orphanet. Accordingly, we developed an automatic approach named SPARE*, for extracting D-P relationships from PubMed abstracts, where phenotypes and RDs are annotated by a Named Entity Recognizer. SPARE* is a hybrid approach that combines a pattern-based method, called SPARE, and a machine learning method (SVM). It benefited both from the relatively good precision of SPARE and from the good recall of the SVM. Second, SPARE* has been used for identifying phenotype candidates from texts. We selected high-quality syntactic patterns that are specific for extracting D-P relationships only. Then, these patterns are relaxed on the phenotype constraint to enable extracting phenotype candidates that are not referenced in databases or ontologies. These candidates are verified and validated by the comparison with phenotype classes in a well-known phenotypic ontology (e.g., HPO). This comparison relies on a compositional semantic model and a set of manually-defined mapping rules for mapping an extracted phenotype candidate to a phenotype term in the ontology. This shows the ability of SPARE* to identify existing and potentially new RD phenotypes. We applied SPARE* on PubMed abstracts to extract RD phenotypes that we either map to the content of Orphanet encyclopedia and Orphadata; or suggest as novel to experts for completing these two resources. Finally, we applied pattern structures for classifying RDs and enriching an existing ontology. First, we used SPARE* to compute the phenotype description of RDs available in Orphadata. We propose comparing and grouping RDs in regard to their phenotypic descriptions, and this by using pattern structures. The pattern structures enable considering both domain knowledge, consisting in a RD ontology and a phenotype ontology, and D-P relationships from various origins. The lattice generated from this pattern structures suggests a new classification of RDs, which in turn suggests new RD classes that do not exist in the original RD ontology. As their number is large, we proposed different selection methods to select a reduced set of interesting RD classes that we suggest for experts for further analysis

University of Macau / Faculty of Science and Technology. / Department of Computer and Information Science