In this thesis, we present an ontology-based information extraction and retrieval system and its application to soccer domain. In general, we deal with three issues in semantic search, namely, usability, scalability and retrieval performance. We propose a keyword-based semantic retrieval approach. The performance of the system is improved considerably using domain-specific information extraction, inference and rules. Scalability is achieved by adapting a semantic indexing approach. The system is implemented using the state-of-the-art technologies in SemanticWeb and its performance is evaluated against traditional systems as well as the query expansion methods. Furthermore, a detailed evaluation is provided to observe the performance gain due to domain-specific information extraction and inference. Finally, we show how we use semantic indexing to solve simple structural ambiguities.

Submitted by Luciana Ferreira (lucgeral@gmail.com) on 2016-02-29T10:48:44Z No. of bitstreams: 2 Dissertação - Walquiria Fernandes Marins - 2015.pdf: 2611919 bytes, checksum: 3d20806ae28d0e0e4c891d8dd65cbd88 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2016-02-29T10:54:01Z (GMT) No. of bitstreams: 2 Dissertação - Walquiria Fernandes Marins - 2015.pdf: 2611919 bytes, checksum: 3d20806ae28d0e0e4c891d8dd65cbd88 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Made available in DSpace on 2016-02-29T10:54:01Z (GMT). No. of bitstreams: 2 Dissertação - Walquiria Fernandes Marins - 2015.pdf: 2611919 bytes, checksum: 3d20806ae28d0e0e4c891d8dd65cbd88 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) Previous issue date: 2015-10-08 / There is an huge amount of data and information stored digitally. Part of this amount of data is available for consultation by Web, however, a significant portion is hidden, due to its storage form, and can’t be recovered by traditional search engines. This makes users face a common and growing challenge to search and find specific information. This challenge is enhanced by the unpreparedness of users to formulate searches and the limitations inherent in research technologies, that because of syntactic differences, can’t find probably relevant data. Aiming to expand the possibilities of semantic interpretation of a query, this work proposes an approach to interpretation of queries in natural language to relational databases through the use of domain ontologies as a tool for their interpretation and semantic enrichment. With the implementation of the approach and its appreciation against a backdrop of queries without the semantic enrichment it is observed that the approach contributes satisfactorily to identify the user’s intention. / Há uma quantidade enorme de dados e informações armazenadas digitalmente. Uma parte desse volume de dados está disponível para consultas através da Web, entretanto, uma parcela significativa está oculta, devido à sua forma de armazenamento, e não pode ser recuperada pelos mecanismos tradicionais de busca. Isso faz com que os usuários enfrentem um desafio comum e crescente para buscar e encontrar informações específicas. Este desafio é potencializado pelo despreparo dos usuários em formular buscas e pelas limitações inerentes às tecnologias de pesquisa que, em virtude de diferenças sintáticas, não conseguem encontrar dados provavelmente relevantes. Visando ampliar as possibilidades de interpretação semântica de uma consulta, este trabalho propõe uma abordagem de interpretação de consultas em linguagem natural a bancos de dados relacionais através do uso de ontologias de domínio como instrumento para sua interpretação e enriquecimento semântico. Com a implementação da abordagem e sua apreciação em relação a um cená- rio de consultas sem o enriquecimento semântico observa-se que a abordagem contribui satisfatoriamente para identificar a intenção do usuário.

Chatbots are computer programs that interact with users utilizing natural language. Businesses benefit from using chatbots as they can provide a better and more satisfactory customer experience. This thesis investigates differences in user satisfaction with two types of e-commerce chatbots: a keyword-based chatbot and a GPT-based chatbot. The study focuses on user interactions with IKEA's chatbot "Billie" compared to a prototype GPT-based chatbot designed for similar functionalities. Using a within-subjects experimental design, participants were tasked with typical e-commerce queries, followed by interviews to gather qualitative data about each participants experience. The research aims to determine whether a chatbot based on GPT technology can offer a more intuitive, engaging and empathetic user experience, compared to traditional keyword-based chatbots in the realm of e-commerce. Findings reveal that the GPT-based chatbot generally provided more accurate and relevant responses, enhancing user satisfaction. Participants appreciated the GPT chatbot's better comprehension and ability to handle natural language, though both systems still exhibited some unnatural interactions. The keyword-based chatbot often failed to understand user intent accurately, leading to user frustration and lower satisfaction. These results suggest that integrating advanced AI technologies like GPT-based chatbots could improve user satisfaction in e-commerce settings, highlighting the potential for more human-like and effective customer service.

La présente thèse s'intéresse à l'utilisation de méta-données textuelles pour l'analyse d'image. Nous cherchons à utiliser ces informations additionelles comme supervision faible pour l'apprentissage de modèles de reconnaissance visuelle. Nous avons observé un récent et grandissant intérêt pour les méthodes capables d'exploiter ce type de données car celles-ci peuvent potentiellement supprimer le besoin d'annotations manuelles, qui sont coûteuses en temps et en ressources. Nous concentrons nos efforts sur deux types de données visuelles associées à des informations textuelles. Tout d'abord, nous utilisons des images de dépêches qui sont accompagnées de légendes descriptives pour s'attaquer à plusieurs problèmes liés à la reconnaissance de visages. Parmi ces problèmes, la vérification de visages est la tâche consistant à décider si deux images représentent la même personne, et le nommage de visages cherche à associer les visages d'une base de données à leur noms corrects. Ensuite, nous explorons des modèles pour prédire automatiquement les labels pertinents pour des images, un problème connu sous le nom d'annotation automatique d'image. Ces modèles peuvent aussi être utilisés pour effectuer des recherches d'images à partir de mots-clés. Nous étudions enfin un scénario d'apprentissage multimodal semi-supervisé pour la catégorisation d'image. Dans ce cadre de travail, les labels sont supposés présents pour les données d'apprentissage, qu'elles soient manuellement annotées ou non, et absentes des données de test. Nos travaux se basent sur l'observation que la plupart de ces problèmes peuvent être résolus si des mesures de similarité parfaitement adaptées sont utilisées. Nous proposons donc de nouvelles approches qui combinent apprentissage de distance, modèles par plus proches voisins et méthodes par graphes pour apprendre, à partir de données visuelles et textuelles, des similarités visuelles spécifiques à chaque problème. Dans le cas des visages, nos similarités se concentrent sur l'identité des individus tandis que, pour les images, elles concernent des concepts sémantiques plus généraux. Expérimentalement, nos approches obtiennent des performances à l'état de l'art sur plusieurs bases de données complexes. Pour les deux types de données considérés, nous montrons clairement que l'apprentissage bénéficie de l'information textuelle supplémentaire résultant en l'amélioration de la performance des systèmes de reconnaissance visuelle.