Im Vergleich zu einer stichwortbasierten Suche ermöglicht die semantische Suche ein präziseres und anspruchsvolleres Durchsuchen von (Web)-Dokumenten, weil durch die explizite Semantik Mehrdeutigkeiten von natürlicher Sprache vermieden und semantische Beziehungen in das Suchergebnis einbezogen werden können. Eine semantische, Entitäten-basierte Suche geht von einer Anfrage mit festgelegter Bedeutung aus und liefert nur Dokumente, die mit dieser Entität annotiert sind als Suchergebnis. Die wichtigste Voraussetzung für eine Entitäten-zentrierte Suche stellt die Annotation der Dokumente im Archiv mit Entitäten und Kategorien dar. Textuelle Informationen werden analysiert und mit den entsprechenden Entitäten und Kategorien versehen, um den Inhalt semantisch erschließen zu können. Eine manuelle Annotation erfordert Domänenwissen und ist sehr zeitaufwendig. Die semantische Annotation von Videodokumenten erfordert besondere Aufmerksamkeit, da inhaltsbasierte Metadaten von Videos aus verschiedenen Quellen stammen, verschiedene Eigenschaften und Zuverlässigkeiten besitzen und daher nicht wie Fließtext behandelt werden können. Die vorliegende Arbeit stellt einen semantischen Analyseprozess für Video-Metadaten vor. Die Eigenschaften der verschiedenen Metadatentypen werden analysiert und ein Konfidenzwert ermittelt. Dieser Wert spiegelt die Korrektheit und die wahrscheinliche Mehrdeutigkeit eines Metadatums wieder. Beginnend mit dem Metadatum mit dem höchsten Konfidenzwert wird der Analyseprozess innerhalb eines Kontexts in absteigender Reihenfolge des Konfidenzwerts durchgeführt. Die bereits analysierten Metadaten dienen als Referenzpunkt für die weiteren Analysen. So kann eine möglichst korrekte Analyse der heterogen strukturierten Daten eines Kontexts sichergestellt werden. Am Ende der Analyse eines Metadatums wird die für den Kontext relevanteste Entität aus einer Liste von Kandidaten identifiziert - das Metadatum wird disambiguiert. Hierfür wurden verschiedene Disambiguierungsalgorithmen entwickelt, die Beschreibungstexte und semantische Beziehungen der Entitätenkandidaten zum gegebenen Kontext in Betracht ziehen. Der Kontext für die Disambiguierung wird für jedes Metadatum anhand der Eigenschaften und Konfidenzwerte zusammengestellt. Der vorgestellte Analyseprozess ist an zwei Hypothesen angelehnt: Um die Analyseergebnisse verbessern zu können, sollten die Metadaten eines Kontexts in absteigender Reihenfolge ihres Konfidenzwertes verarbeitet werden und die Kontextgrenzen von Videometadaten sollten durch Segmentgrenzen definiert werden, um möglichst Kontexte mit kohärentem Inhalt zu erhalten. Durch ausführliche Evaluationen konnten die gestellten Hypothesen bestätigt werden. Der Analyseprozess wurden gegen mehrere State-of-the-Art Methoden verglichen und erzielt verbesserte Ergebnisse in Bezug auf Recall und Precision, besonders für Metadaten, die aus weniger zuverlässigen Quellen stammen. Der Analyseprozess ist Teil eines Videoanalyse-Frameworks und wurde bereits erfolgreich in verschiedenen Projekten eingesetzt. / The Semantic Web provides information contained in the World Wide Web as machine-readable facts. In comparison to a keyword-based inquiry, semantic search enables a more sophisticated exploration of web documents. By clarifying the meaning behind entities, search results are more precise and the semantics simultaneously enable an exploration of semantic relationships. However, unlike keyword searches, a semantic entity-focused search requires that web documents are annotated with semantic representations of common words and named entities. Manual semantic annotation of (web) documents is time-consuming; in response, automatic annotation services have emerged in recent years. These annotation services take continuous text as input, detect important key terms and named entities and annotate them with semantic entities contained in widely used semantic knowledge bases, such as Freebase or DBpedia. Metadata of video documents require special attention. Semantic analysis approaches for continuous text cannot be applied, because information of a context in video documents originates from multiple sources possessing different reliabilities and characteristics. This thesis presents a semantic analysis approach consisting of a context model and a disambiguation algorithm for video metadata. The context model takes into account the characteristics of video metadata and derives a confidence value for each metadata item. The confidence value represents the level of correctness and ambiguity of the textual information of the metadata item. The lower the ambiguity and the higher the prospective correctness, the higher the confidence value. The metadata items derived from the video metadata are analyzed in a specific order from high to low confidence level. Previously analyzed metadata are used as reference points in the context for subsequent disambiguation. The contextually most relevant entity is identified by means of descriptive texts and semantic relationships to the context. The context is created dynamically for each metadata item, taking into account the confidence value and other characteristics. The proposed semantic analysis follows two hypotheses: metadata items of a context should be processed in descendent order of their confidence value, and the metadata that pertains to a context should be limited by content-based segmentation boundaries. The evaluation results support the proposed hypotheses and show increased recall and precision for annotated entities, especially for metadata that originates from sources with low reliability. The algorithms have been evaluated against several state-of-the-art annotation approaches. The presented semantic analysis process is integrated into a video analysis framework and has been successfully applied in several projects for the purpose of semantic video exploration of videos.

Submitted by Renata Lopes (renatasil82@gmail.com) on 2016-02-05T16:40:06Z No. of bitstreams: 1 elyedisondasilvamatos.pdf: 5520917 bytes, checksum: c9e7d798d96928a6ad4f2ee48d912531 (MD5) / Approved for entry into archive by Adriana Oliveira (adriana.oliveira@ufjf.edu.br) on 2016-02-26T11:51:46Z (GMT) No. of bitstreams: 1 elyedisondasilvamatos.pdf: 5520917 bytes, checksum: c9e7d798d96928a6ad4f2ee48d912531 (MD5) / Made available in DSpace on 2016-02-26T11:51:47Z (GMT). No. of bitstreams: 1 elyedisondasilvamatos.pdf: 5520917 bytes, checksum: c9e7d798d96928a6ad4f2ee48d912531 (MD5) Previous issue date: 2014-06-27 / Enquanto no âmbito da Sintaxe, as técnicas, os algoritmos e as aplicações em Processamento da Língua Natural são bem estudados e já estão relativamente bem estabelecidos, no âmbito da Semântica não é possível observar ainda a mesma maturidade. Visando, então, contribuir para os estudos em Semântica Computacional, este trabalho busca maneiras de implementar algumas das ideias e dos insights propostos pela Linguística Cognitiva, que é, por si, uma alternativa à Linguística Gerativa. A tentativa é reunir algumas das ferramentas disponíveis, seja no viés computacional (Bancos de Dados, Teoria dos Grafos, Ontologias, Mecanismos de inferências, Modelos Conexionistas), seja no viés linguístico (Semântica de Frames e Teoria do Léxico Gerativo), seja no viés de aplicações (FrameNet e ontologia SIMPLE), a fim de abordar as questões semânticas de forma mais flexível. O objeto de estudo é o processo de desambiguação de Unidades Lexicais. O resultado da pesquisa realizada é corporificado na forma de uma aplicação computacional, chamada Framework LUDI (Lexical Unit Discovery through Inference), composta por algoritmos e estruturas de dados usados na desambiguação. O framework é uma aplicação de Compreensão da Língua Natural, que pode ser integrada em ferramentas para recuperação de informação e sumarização, bem como em processos de Etiquetagem de Papéis Semânticos (SRL - Semantic Role Labeling). / While in the field of Syntax techniques, algorithms and applications in Natural Language Processing are well known and relatively well established, the same situation does not hold for the field of Semantics. Aiming at contributing to the studies in Computational Semantics, this work implements ideas and insights offered by Cognitive Linguistics, which is itself an alternative to Generative Linguistics. We attempt to bring together contributions from the computational domain (Databases, Graph Theory, Ontologies, inference mechanisms, Connectionists Models), the linguistic domain (Frame Semantics and the Generative Lexicon), and the application domain (FrameNet and SIMPLE Ontology) in order to address the semantic issues more flexibly. The object of study is the process of disambiguation of Lexical Units. The results of the research are embodied in the form of a computer application, called Framework LUDI (Lexical Unit Discovery through Inference), and composed of algorithms and data structures used for Lexical Unit disambiguation. The framework is an application of Natural Language Understanding, which can be integrated into information retrieval and summarization tools, as well as into processes of Semantic Role Labeling (SRL).

Made available in DSpace on 2016-03-15T19:37:43Z (GMT). No. of bitstreams: 1 Ana Carolina Espirito Santo Lima.pdf: 2485278 bytes, checksum: 9843b9f756f82c023af6a2ee291f2b1d (MD5) Previous issue date: 2012-12-14 / Fundação de Amparo a Pesquisa do Estado de São Paulo / Social media have become a way of expressing collective interests. People are motivated by the sharing of information and the feedback from friends and colleagues. Among the many social media tools available, the Twitter microblog is gaining popularity as a platform for in-stantaneous communication. Millions of messages are generated daily, from over 100 million users, about the most varied subjects. As it is a rapid communication platform, this microblog spurred a phenomenon called television storytellers, where surfers comment on what they watch on TV while the programs are being transmitted. The Social TV emerged from this integration between social media and television. The amount of data generated on the TV shows is a rich material for data analysis. Broadcasters may use such information to improve their programs and increase interaction with their audience. Among the main challenges in social media data analysis there is sentiment analysis (to determine the polarity of a text, for instance, positive or negative), and sense disambiguation (to determine the right context of polysemic words). This dissertation aims to use machine learning techniques to create a tool to support Social TV, contributing specifically to the automation of sentiment analysis and disambiguation of Twitter messages. / As mídias sociais são uma forma de expressão dos interesses coletivos, as pessoas gostam de compartilhar informações e sentem-se valorizadas por causa disso. Entre as mídias sociais o microblog Twitter vem ganhando popularidade como uma plataforma para comunicação ins-tantânea. São milhões de mensagens geradas todos os dias, por cerca de 100 milhões de usuá-rios, carregadas dos mais diversos assuntos. Por ser uma plataforma de comunicação rápida esse microblog estimulou um fenômeno denominado narradores televisivos, em que os inter-nautas comentam sobre o que assistem na TV no momento em que é transmitido. Dessa inte-gração entre as mídias sociais e a televisão emergiu a TV Social. A quantidade de dados gera-dos sobre os programas de TV formam um rico material para análise de dados. Emissoras podem usar tais informações para aperfeiçoar seus programas e aumentar a interação com seu público. Dentre os principais desafios da análise de dados de mídias sociais encontram-se a análise de sentimento (determinação de polaridade em um texto, por exemplo, positivo ou negativo) e a desambiguação de sentido (determinação do contexto correto de palavras polis-sêmicas). Essa dissertação tem como objetivo usar técnicas de aprendizagem de máquina para a criação de uma ferramenta de apoio à TV Social com contribuições na automatização dos processos de análise de sentimento e desambiguação de sentido de mensagens postadas no Twitter.

A comunicação multilíngue é uma tarefa cada vez mais imperativa no cenário atual de grande disseminação de informações em diversas línguas. Nesse contexto, são de grande relevância os sistemas de tradução automática, que auxiliam tal comunicação, automatizando-a. Apesar de ser uma área de pesquisa bastante antiga, a Tradução Automática ainda apresenta muitos problemas. Um dos principais problemas é a ambigüidade lexical, ou seja, a necessidade de escolha de uma palavra, na língua alvo, para traduzir uma palavra da língua fonte quando há várias opções de tradução. Esse problema se mostra ainda mais complexo quando são identificadas apenas variações de sentido nas opções de tradução. Ele é denominado, nesse caso, \"ambigüidade lexical de sentido\". Várias abordagens têm sido propostas para a desambiguação lexical de sentido, mas elas são, em geral, monolíngues (para o inglês) e independentes de aplicação. Além disso, apresentam limitações no que diz respeito às fontes de conhecimento que podem ser exploradas. Em se tratando da língua portuguesa, em especial, não há pesquisas significativas voltadas para a resolução desse problema. O objetivo deste trabalho é a proposta e desenvolvimento de uma nova abordagem de desambiguação lexical de sentido, voltada especificamente para a tradução automática, que segue uma metodologia híbrida (baseada em conhecimento e em córpus) e utiliza um formalismo relacional para a representação de vários tipos de conhecimentos e de exemplos de desambiguação, por meio da técnica de Programação Lógica Indutiva. Experimentos diversos mostraram que a abordagem proposta supera abordagens alternativas para a desambiguação multilíngue e apresenta desempenho superior ou comparável ao do estado da arte em desambiguação monolíngue. Adicionalmente, tal abordagem se mostrou efetiva como mecanismo auxiliar para a escolha lexical na tradução automática estatística / Crosslingual communication has become a very imperative task in the current scenario with the increasing amount of information dissemination in several languages. In this context, machine translation systems, which can facilitate such communication by providing automatic translations, are of great importance. Although research in Machine Translation dates back to the 1950\'s, the area still has many problems. One of the main problems is that of lexical ambiguity, that is, the need for lexical choice when translating a source language word that has several translation options in the target language. This problem is even more complex when only sense variations are found in the translation options, a problem named \"sense ambiguity\". Several approaches have been proposed for word sense disambiguation, but they are in general monolingual (for English) and application-independent. Moreover, they have limitations regarding the types of knowledge sources that can be exploited. Particularly, there is no significant research aiming to word sense disambiguation involving Portuguese. The goal of this PhD work is the proposal and development of a novel approach for word sense disambiguation which is specifically designed for machine translation, follows a hybrid methodology (knowledge and corpus-based), and employs a relational formalism to represent various kinds of knowledge sources and disambiguation examples, by using Inductive Logic Programming. Several experiments have shown that the proposed approach overcomes alternative approaches in multilingual disambiguation and achieves higher or comparable results to the state of the art in monolingual disambiguation. Additionally, the approach has shown to effectively assist lexical choice in a statistical machine translation system

No description available.

We describe the automatic acquisition of a semantic network in which over 7,500 of the most frequently occurring nouns in the English language are linked to their semantically related concepts in the WordNet noun ontology. Relatedness between nouns is discovered automatically from lexical co-occurrence in Wikipedia texts using a novel adaptation of an information theoretic inspired measure. Our algorithm then capitalizes on salient sense clustering among these semantic associates to automatically disambiguate them to their corresponding WordNet noun senses (i.e., concepts). The resultant concept-to-concept associations, stemming from 7,593 target nouns, with 17,104 distinct senses among them, constitute a large-scale semantic network with 208,832 undirected edges between related concepts. Our work can thus be conceived of as augmenting the WordNet noun ontology with RelatedTo links. The network, which we refer to as the Szumlanski-Gomez Network (SGN), has been subjected to a variety of evaluative measures, including manual inspection by human judges and quantitative comparison to gold standard data for semantic relatedness measurements. We have also evaluated the network’s performance in an applied setting on a word sense disambiguation (WSD) task in which the network served as a knowledge source for established graph-based spreading activation algorithms, and have shown: a) the network is competitive with WordNet when used as a stand-alone knowledge source for WSD, b) combining our network with WordNet achieves disambiguation results that exceed the performance of either resource individually, and c) our network outperforms a similar resource, WordNet++ (Ponzetto & Navigli, 2010), that has been automatically derived from annotations in the Wikipedia corpus. iii Finally, we present a study on human perceptions of relatedness. In our study, we elicited quantitative evaluations of semantic relatedness from human subjects using a variation of the classical methodology that Rubenstein and Goodenough (1965) employed to investigate human perceptions of semantic similarity. Judgments from individual subjects in our study exhibit high average correlation to the elicited relatedness means using leave-one-out sampling (r = 0.77, σ = 0.09, N = 73), although not as high as average human correlation in previous studies of similarity judgments, for which Resnik (1995) established an upper bound of r = 0.90 (σ = 0.07, N = 10). These results suggest that human perceptions of relatedness are less strictly constrained than evaluations of similarity, and establish a clearer expectation for what constitutes human-like performance by a computational measure of semantic relatedness. We also contrast the performance of a variety of similarity and relatedness measures on our dataset to their performance on similarity norms and introduce our own dataset as a supplementary evaluative standard for relatedness measures.

No description available.

With the ever increase in biomedical literature, text-mining has emerged as an important technology to support bio-curation and search. Word sense disambiguation (WSD), the correct identification of terms in text in the light of ambiguity, is an important problem in text-mining. Since the late 1940s many approaches based on supervised (decision trees, naive Bayes, neural networks, support vector machines) and unsupervised machine learning (context-clustering, word-clustering, co-occurrence graphs) have been developed. Knowledge-based methods that make use of the WordNet computational lexicon have also been developed. But only few make use of ontologies, i.e. hierarchical controlled vocabularies, to solve the problem and none exploit inference over ontologies and the use of metadata from publications. This thesis addresses the WSD problem in biomedical ontologies by suggesting different approaches for word sense disambiguation that use ontologies and metadata. The "Closest Sense" method assumes that the ontology defines multiple senses of the term; it computes the shortest path of co-occurring terms in the document to one of these senses. The "Term Cooc" method defines a log-odds ratio for co-occurring terms including inferred co-occurrences. The "MetaData" approach trains a classifier on metadata; it does not require any ontology, but requires training data, which the other methods do not. These approaches are compared to each other when applied to a manually curated training corpus of 2600 documents for seven ambiguous terms from the Gene Ontology and MeSH. All approaches over all conditions achieve 80% success rate on average. The MetaData approach performs best with 96%, when trained on high-quality data. Its performance deteriorates as quality of the training data decreases. The Term Cooc approach performs better on Gene Ontology (92% success) than on MeSH (73% success) as MeSH is not a strict is-a/part-of, but rather a loose is-related-to hierarchy. The Closest Sense approach achieves on average 80% success rate. Furthermore, the thesis showcases applications ranging from ontology design to semantic search where WSD is important.

Η συγκεκριμένη διατριβή στοχεύει στον σχεδιασμό της μεθοδολογίας που θα εφαρμοστεί για την υλοποίηση ενός προσκομιστή πληροφορίας από τον Παγκόσμιο Ιστό, ο οποίος θα λειτουργεί λαμβάνοντας υπόψη θεματικά κριτήρια. Τέτοιου είδους προγράμματα ανίχνευσης πληροφορίας, είναι ευρέως γνωστά ως θεματικά εστιασμένοι προσκομιστές ιστοσελίδων. Κατά τη διάρκεια της μελέτης μας, σχεδιάσαμε και υλοποιήσαμε ένα καινοτόμο σύστημα θεματικής κατηγοριοποίησης ιστοσελίδων που κάνει εκτεταμένη χρήση των σημασιολογικών δεδομένων τα οποία περιέχονται στο σημασιολογικό δίκτυο WordNet. Η απόφαση για την αξιοποίηση του WordNet ελήφθη με τη φιλοδοξία να αντιμετωπιστούν αποτελεσματικά φαινόμενα ασάφειας εννοιών που μειώνουν τις επιδόσεις των διαθέσιμων θεματικών κατηγοριοποιητών. Η καταλληλότητα του WordNet για την επίλυση της σημασιολογικής ασάφειας έχει αποδειχθεί στο παρελθόν, αλλά ποτέ δεν εξετάστηκε σε ένα σύστημα εστιασμένης προσκόμισης ιστοσελίδων με τον συγκεκριμένο τρόπο, ενώ ποτέ δεν έχει αξιοποιηθεί στην κατηγοριοποίηση ιστοσελίδων για την ελληνική γλώσσα. Ως εκ τούτου, ο θεματικός κατηγοριοποιητής που υλοποιήσαμε, και κατά συνέπεια, και ο εστιασμένος προσκομιστής στον οποίο ενσωματώνεται ο κατηγοριοποιητής, είναι καινοτόμοι όσο αφορά τον τρόπο με τον οποίο αποσαφηνίζουν έννοιες λέξεων με στόχο την αποτελεσματική ανίχνευση του θεματικού προσανατολισμού μίας ιστοσελίδας . Ένας προσκομιστής ιστοσελίδων είναι ένα πρόγραμμα που με αφετηρία μία λίστα διευθύνσεων ιστοσελίδων (URLs) αρχικοποίησης προσκομίζει το περιεχόμενο των ιστοσελίδων που συναντά και συνεχίζει ακολουθώντας τους εσωτερικούς τους συνδέσμους με απώτερο σκοπό την προσκόμιση όσο το δυνατό μεγαλύτερου υποσυνόλου δεδομένων του Παγκόσμιου Ιστού (ανάλογα με τους διαθέσιμους πόρους, την χωρητικότητα του δικτύου, κλπ.). Δεδομένου ότι ο όγκος των δεδομένων που είναι διαθέσιμα στον Παγκόσμιο Ιστό αυξάνεται με εκθετικό ρυθμό, είναι πρακτικά αδύνατο να προσκομιστούν όλες οι ζητούμενες πηγές πληροφορίας ανά πάσα στιγμή. Ένας τρόπος για να αντιμετωπίσουμε το συγκεκριμένο πρόβλημα είναι η εκμετάλλευση συστημάτων εστιασμένης προσκόμισης ιστοσελίδων που στοχεύουν στη λήψη ιστοσελίδων συγκεκριμένης θεματολογίας που εκφράζουν κάθε φορά το θεματικό προφίλ του χρήστη, σε αντίθεση με τους προσκομιστές ιστοσελίδων γενικού σκοπού που καταναλώνουν πόρους άσκοπα προσπαθώντας να προσκομίσουν κάθε πιθανή πηγή πληροφορίας που συναντούν. Οι εστιασμένοι προσκομιστές χρησιμοποιούνται εκτενώς, για την κατασκευή θεματικά προσανατολισμένων ευρετηρίων ιστοσελίδων, κάθε ένα από τα οποία έχει την δυνατότητα να εξυπηρετήσει αιτήσεις χρηστών με συγκεκριμένο θεματικό προσανατολισμό. Με αυτό τον τρόπο είναι δυνατόν να αντιμετωπιστεί το πρόβλημα της υπερφόρτωσης πληροφοριών. Προκειμένου να επιτελέσουμε την συγκεκριμένη εργασία μελετήσαμε εκτενώς υπάρχουσες τεχνικές εστιασμένης προσκόμισης, στις οποίες στηριχθήκαμε ώστε να ορίσουμε την μεθοδολογία που θα ακολουθήσουμε. Το αποτέλεσμα είναι η υλοποίηση ενός θεματικά εστιασμένου πολυνηματικού προσκομιστή, ο οποίος ενσωματώνει τις εξής καινοτομίες: είναι ρυθμισμένος προκειμένου να εκτελεί εστιασμένες προσκομίσεις σε ιστοσελίδες ελληνικού ενδιαφέροντος, αποσαφηνίζει το κείμενο που αντιστοιχεί σε ιστοσελίδες προκειμένου να ανακαλύψει τον θεματικό τους προσανατολισμό. Επιπλέον προτείνουμε μία σειρά υποσυστημάτων τα οποία θα μπορούσαν να ενσωματωθούν στο σύστημα εστιασμένης προσκόμισης προκειμένου να ενισχύσουμε την απόδοσή του. Τέτοια συστήματα είναι το υποσύστημα ανίχνευσης όψεων που αντιστοιχίζονται σε επώνυμες οντότητες καθώς και το υποσύστημα εξαγωγής λέξεων κλειδιών που μπορούν να χρησιμοποιηθούν ως χαρακτηριστικά κατηγοριοποίσης από το αλφαριθμητικό των διευθύνσεων (URL) ιστοσελίδων. Για να παρουσιάσουμε την αποτελεσματικότητα της προτεινόμενης μεθόδου, διενεργήσαμε μία σειρά πειραματικών μετρήσεων. Συγκεκριμένα αξιολογήσαμε πειραματικά τα ακόλουθα: την αποτελεσματικότητα του αλγορίθμου αποσαφήνισης που ενσωματώσαμε στον προσκομιστή, την απόδοση του θεματικού κατηγοριοποιητή ο οποίος καθορίζει την συμπεριφορά του εστιασμένου προσκομιστή σχετικά με το αν μια σελίδα θα πρέπει να κατέβει ως θεματικά σχετική με το θέμα ενδιαφέροντος ή όχι, την απόδοση του εστιασμένου προσκομιστή καταγράφοντας τον ρυθμό απόκτησης που επιτυγχάνει κατά την διάρκεια της εστιασμένης προσκόμισης χρησιμοποιώντας κάθε φορά διαφορετικά χαρακτηριστικά κατηγοριοποίησης, την καταλληλότητα του υποσυστήματος εξαγωγής λέξεων-κλειδιών από το αλφαριθμητικό URL για την περιγραφή του θεματικού προσανατολισμού της ιστοσελίδας και τέλος τη χρησιμότητα του συστήματος αναγνώρισης επώνυμων οντοτήτων στην οργάνωση ιστοσελίδων των οποίων η σημασιολογία δεν αναπαρίσταται ικανοποιητικά σε σημασιολογικούς πόρους γενικού σκοπού συμπεριλαμβανομένου του σημασιολογικού δικτύου WordNet. Τα πειραματικά αποτελέσματα επιβεβαιώνουν τη συμβολή του θεματικά εστιασμένου προσκομιστή που προτείνουμε στην προσκόμιση περιεχομένου ειδικού ενδιαφέροντος από τον Παγκόσμιο Ιστό. Παράλληλα αποδεικνύουμε ότι όλες οι μέθοδοι που ενσωματώσαμε στο σύστημα εστιασμένης προσκόμισης είναι δυνατό να συνεργαστούν κατά τρόπο που να βελτιώνει την απόδοση του προσκομιστή . Τέλος από τα πειραματικά αποτελέσματα αποδεικνύεται ότι η προτεινόμενη τεχνική είναι εξίσου αποτελεσματική για ιστοσελίδες στα αγγλικά και στα ελληνικά. Επιπλέον πιστεύουμε ότι μπορεί να εφαρμοστεί με επιτυχία και σε ιστοσελίδες που περιέχουν κείμενα άλλων φυσικών γλωσσών, με προϋπόθεση την ύπαρξη σημασιολογικών πόρων, αντίστοιχων με το WordNet και διαθέσιμων εργαλείων που θα επιτρέπουν την ανάλυση των δεδομένων κειμένου τους. / This dissertation aims at the specification of an algorithmic methodology that will be applied towards the implementation of a web crawler, which will operate upon thematic criteria. Such crawlers are widely known as topical focused web crawlers. To realize our objective, the utilization of a web page thematic classification system (either existing or newly developed one) is imperative. In the course of our study, we designed and implemented a novel thematic classifier that makes extensive use of the semantic data encoded in WordNet semantic network and such decision was taken with the aspiration of tackling effectively sense ambiguity phenomena that degrade the performance of available classifiers. The suitability of WordNet towards resolving semantic ambiguity has been previously proven but never examined in a focused web crawling application and has never been exploited for the Greek language. Therefore, our thematic classifier and consequently our focused crawler that integrates it are innovative in the way in which they perform word sense disambiguation for achieving the effective detection of the web page topics (themes). In a broad sense, a web crawler is a program that based on a seed list of URLs it downloads the contents of the web pages it comes across and continues following their internal links with the utmost objective of fetching as much as web data as possible (depending on available resources, network capacity, etc.). Given that the web data grows at exponential rates, it is practically impossible to download all the web sources at any given time. One way to tackle such difficulty is to implement and employ topical focused crawlers that aim at downloading content of specific topics (potentially of interest to the user) rather than waste resources trying to download every single data source that is available on the web. Topically focused crawlers are extensively used for building topical focused indices, each of which can serve specialized user search requests, therefore dealing partially with the information overload problem. To carry out our work, we have extensively reviewed existing approaches with respect to topically focused crawling techniques upon which we relied for defining our own focused crawling methodology, which resulted into the implementation of a topical focused crawler that incorporates the following innovate features: it is tailored to operate on the Greek web, it disambiguates the web pages in order to uncover their topic and it incorporates numerous features, such as a named entities recognizer, a URL keyword extractor, personalization techniques, etc., in order to maximize its performance. To demonstrate the effectiveness of our method, we have applied our topical focused crawler on several datasets and experimentally evaluated the following issues: the efficiency of the sense resolution algorithm incorporated into our crawler, the performance of the topical classifier that the crawler consults prior to making a final decision as to whether a page should be downloaded as topically relevant to a subject of interest or not, the suitability of the URL keyword extractor module for judging the subject of a web page based entirely on the analysis of its URL, the usefulness of the named entities recognizer in organizing pages whose semantics are poorly represented within the contents of general-purpose semantic resources (including WordNet semantic network). Experimental results confirm the contribution of our topically focused crawler in downloading web content of specific interest and show that all the methods and techniques that we have successfully integrated into the crawler can interoperate with its other in a manner that improves the crawling performance while allowing for flexibility in the downloading process at the same time. Last but not least, experimental results showcase that our crawling methodology is equally effective for both English and Greek and we believe that it can be fruitfully applied to other natural languages provided that there the respective semantic resources and tools are available for analyzing their textual data.

With the ever increase in biomedical literature, text-mining has emerged as an important technology to support bio-curation and search. Word sense disambiguation (WSD), the correct identification of terms in text in the light of ambiguity, is an important problem in text-mining. Since the late 1940s many approaches based on supervised (decision trees, naive Bayes, neural networks, support vector machines) and unsupervised machine learning (context-clustering, word-clustering, co-occurrence graphs) have been developed. Knowledge-based methods that make use of the WordNet computational lexicon have also been developed. But only few make use of ontologies, i.e. hierarchical controlled vocabularies, to solve the problem and none exploit inference over ontologies and the use of metadata from publications. This thesis addresses the WSD problem in biomedical ontologies by suggesting different approaches for word sense disambiguation that use ontologies and metadata. The "Closest Sense" method assumes that the ontology defines multiple senses of the term; it computes the shortest path of co-occurring terms in the document to one of these senses. The "Term Cooc" method defines a log-odds ratio for co-occurring terms including inferred co-occurrences. The "MetaData" approach trains a classifier on metadata; it does not require any ontology, but requires training data, which the other methods do not. These approaches are compared to each other when applied to a manually curated training corpus of 2600 documents for seven ambiguous terms from the Gene Ontology and MeSH. All approaches over all conditions achieve 80% success rate on average. The MetaData approach performs best with 96%, when trained on high-quality data. Its performance deteriorates as quality of the training data decreases. The Term Cooc approach performs better on Gene Ontology (92% success) than on MeSH (73% success) as MeSH is not a strict is-a/part-of, but rather a loose is-related-to hierarchy. The Closest Sense approach achieves on average 80% success rate. Furthermore, the thesis showcases applications ranging from ontology design to semantic search where WSD is important.