Generating computer animation from natural language instructions is a complex task that encompasses several key aspects of artificial intelligence including natural language understanding, computer graphics and knowledge representation. Traditionally, this task has been approached using rule based systems which were highly successful on their respective domains, but were difficult to generalise to other domains. In this thesis, I describe the key theories and principles behind a domain-independent machine learning framework for constructing natural language based animation systems, and show how this framework can be more flexible and more powerful than the prevalent rule based approach. / I begin this thesis with a thorough introduction to the goals of the research. I then review the most relevant literature to put this research into perspective. After the literature review, I provide brief descriptions to the most relevant technologies in both natural language processing and computer graphics. I then report original research in semantic role labelling and verb sense disambiguation, followed by a detailed description and analysis of the machine learning framework for natural language based animation generation. / The key contributions of this thesis are: a novel method for performing semantic role labelling of prepositional phrases, a novel method for performing verb sense disambiguation, and a novel machine learning framework for grounding linguistic information in virtual worlds and converting verb-semantic information to computer graphics commands to create computer animation.

Word sense disambiguation (WSD) is the process of computationally identifying and labeling poly- semous words in context with their correct meaning, known as a sense. WSD is riddled with various obstacles that must be overcome in order to reach its full potential. One of these problems is the aspect of the representation of word meaning. Traditional WSD algorithms make the assumption that a word in a given context has only one meaning and therfore can return only one discrete sense. On the other hand, a novel approach is that a given word can have multiple senses. Studies on graded word sense assignment (Erk et al., 2009) as well as in cognitive science (Hampton, 2007; Murphy, 2002) support this theory. It has therefore been adopted in a novel, paraphrasing system which performs word sense disambiguation by returning a probability distribution over potential paraphrases (in this case synonyms) of a given word. However, it is unknown how well this type of algorithm fares against the traditional one. The current study thus examines if and how it is possible to make a comparison of the two. A method of comparison is evaluated and subsequently rejected. Reasons for this as well as suggestions for a fair and accurate comparison are presented.

Natural language is inherently ambiguous. For example, the word "bank" can mean a financial institution or a river shore. Finding the correct meaning of a word in a particular context is a task known as word sense disambiguation (WSD), which is essential for many natural language processing applications such as machine translation, information retrieval, and others. While most current WSD methods try to disambiguate a small number of words for which enough annotated examples are available, the method proposed in this thesis attempts to address all words in unrestricted text. The method is based on constraints imposed by syntactic dependencies and concept generalizations drawn from an external dictionary. The method was tested on standard benchmarks as used during the SENSEVAL-2 and SENSEVAL-3 WSD international evaluation exercises, and was found to be competitive.

The use of Conversational Agents (CAs) utilizing Artificial Intelligence Markup Language (AIML) has been studied in a number of disciplines. Previous research has shown a great deal of promise. It has also documented significant limitations in the abilities of these CAs. Many of these limitations are related specifically to the method employed by AIML to resolve ambiguities in the meaning and context of words. While methods exist to detect and correct common errors in spelling and grammar of sentences and queries submitted by a user, one class of input error that is particularly difficult to detect and correct is the malapropism. In this research a malapropism is defined a "verbal blunder in which one word is replaced by another similar in sound but different in meaning" ("malapropism," 2013). This research explored the use of alternative methods of correcting malapropisms in sentences input to AIML CAs using measures of Semantic Distance and tri-gram probabilities. Results of these alternate methods were compared against AIML CAs using only the Symbolic Reductions built into AIML. This research found that the use of the two methodologies studied here did indeed lead to a small, but measurable improvement in the performance of the CA in terms of the appropriateness of its responses as classified by human judges. However, it was also noted that in a large number of cases, the CA simply ignored the existence of a malapropism altogether in formulating its responses. In most of these cases, the interpretation and response to the user's input was of such a general nature that one might question the overall efficacy of the AIML engine. The answer to this question is a matter for further study.

Hypothetically, if you were told: Apple uses the apple as its logo . You would immediately detect two different senses of the word apple , these being the company and the fruit respectively. Making this distinction is the formidable challenge of Word Sense Disambiguation (WSD), which is the subtask of many Natural Language Processing (NLP) applications. This thesis is a multi-branched investigation into WSD, that explores and evaluates unsupervised knowledge-based methods that exploit semantic subgraphs. The nature of research covered by this thesis can be broken down to: 1. Mining data from the encyclopedic resource Wikipedia, to visually prove the existence of context embedded in semantic subgraphs 2. Achieving disambiguation in order to merge concepts that originate from heterogeneous semantic graphs 3. Participation in international evaluations of WSD across a range of languages 4. Treating WSD as a classification task, that can be optimised through the iterative construction of semantic subgraphs The contributions of each chapter are ranged, but can be summarised by what has been produced, learnt, and raised throughout the thesis. Furthermore an API and several resources have been developed as a by-product of this research, all of which can be accessed by visiting the author’s home page at http://www.stevemanion.com. This should enable researchers to replicate the results achieved in this thesis and build on them if they wish.

Since the proposal of hypertext by Tim Berners-Lee to his employer CERN on March 12, 1989 the World Wide Web has grown to more than one billion Web pages and still grows. With the later proposed Semantic Web vision,Berners-Lee et al. suggested an extension of the existing (Document) Web to allow better reuse, sharing and understanding of data. Both the Document Web and the Web of Data (which is the current implementation of the Semantic Web) grow continuously. This is a mixed blessing, as the two forms of the Web grow concurrently and most commonly contain different pieces of information. Modern information systems must thus bridge a Semantic Gap to allow a holistic and unified access to information about a particular information independent of the representation of the data. One way to bridge the gap between the two forms of the Web is the extraction of structured data, i.e., RDF, from the growing amount of unstructured and semi-structured information (e.g., tables and XML) on the Document Web. Note, that unstructured data stands for any type of textual information like news, blogs or tweets. While extracting structured data from unstructured data allows the development of powerful information system, it requires high-quality and scalable knowledge extraction frameworks to lead to useful results. The dire need for such approaches has led to the development of a multitude of annotation frameworks and tools. However, most of these approaches are not evaluated on the same datasets or using the same measures. The resulting Evaluation Gap needs to be tackled by a concise evaluation framework to foster fine-grained and uniform evaluations of annotation tools and frameworks over any knowledge bases. Moreover, with the constant growth of data and the ongoing decentralization of knowledge, intuitive ways for non-experts to access the generated data are required. Humans adapted their search behavior to current Web data by access paradigms such as keyword search so as to retrieve high-quality results. Hence, most Web users only expect Web documents in return. However, humans think and most commonly express their information needs in their natural language rather than using keyword phrases. Answering complex information needs often requires the combination of knowledge from various, differently structured data sources. Thus, we observe an Information Gap between natural-language questions and current keyword-based search paradigms, which in addition do not make use of the available structured and unstructured data sources. Question Answering (QA) systems provide an easy and efficient way to bridge this gap by allowing to query data via natural language, thus reducing (1) a possible loss of precision and (2) potential loss of time while reformulating the search intention to transform it into a machine-readable way. Furthermore, QA systems enable answering natural language queries with concise results instead of links to verbose Web documents. Additionally, they allow as well as encourage the access to and the combination of knowledge from heterogeneous knowledge bases (KBs) within one answer. Consequently, three main research gaps are considered and addressed in this work: First, addressing the Semantic Gap between the unstructured Document Web and the Semantic Gap requires the development of scalable and accurate approaches for the extraction of structured data in RDF. This research challenge is addressed by several approaches within this thesis. This thesis presents CETUS, an approach for recognizing entity types to populate RDF KBs. Furthermore, our knowledge base-agnostic disambiguation framework AGDISTIS can efficiently detect the correct URIs for a given set of named entities. Additionally, we introduce REX, a Web-scale framework for RDF extraction from semi-structured (i.e., templated) websites which makes use of the semantics of the reference knowledge based to check the extracted data. The ongoing research on closing the Semantic Gap has already yielded a large number of annotation tools and frameworks. However, these approaches are currently still hard to compare since the published evaluation results are calculated on diverse datasets and evaluated based on different measures. On the other hand, the issue of comparability of results is not to be regarded as being intrinsic to the annotation task. Indeed, it is now well established that scientists spend between 60% and 80% of their time preparing data for experiments. Data preparation being such a tedious problem in the annotation domain is mostly due to the different formats of the gold standards as well as the different data representations across reference datasets. We tackle the resulting Evaluation Gap in two ways: First, we introduce a collection of three novel datasets, dubbed N3, to leverage the possibility of optimizing NER and NED algorithms via Linked Data and to ensure a maximal interoperability to overcome the need for corpus-specific parsers. Second, we present GERBIL, an evaluation framework for semantic entity annotation. The rationale behind our framework is to provide developers, end users and researchers with easy-to-use interfaces that allow for the agile, fine-grained and uniform evaluation of annotation tools and frameworks on multiple datasets. The decentral architecture behind the Web has led to pieces of information being distributed across data sources with varying structure. Moreover, the increasing the demand for natural-language interfaces as depicted by current mobile applications requires systems to deeply understand the underlying user information need. In conclusion, the natural language interface for asking questions requires a hybrid approach to data usage, i.e., simultaneously performing a search on full-texts and semantic knowledge bases. To close the Information Gap, this thesis presents HAWK, a novel entity search approach developed for hybrid QA based on combining structured RDF and unstructured full-text data sources.

La problématique traitée dans la thèse s’inscrit dans le cadre de l’analyse d’usage dans les systèmes de recherche d’information. En effet, nous nous intéressons à l’utilisateur à travers l’historique de ses requêtes, utilisées comme support d’analyse pour l’extraction d'un profil d’usage. L’objectif est de caractériser l’utilisateur et les sources de données qui interagissent dans un réseau afin de permettre des comparaisons utilisateur-utilisateur, source-source et source-utilisateur. Selon une étude que nous avons menée sur les travaux existants sur les modèles de profilage, nous avons conclu que la grande majorité des contributions sont fortement liés aux applications dans lesquelles ils étaient proposés. En conséquence, les modèles de profils proposés ne sont pas réutilisables et présentent plusieurs faiblesses. Par exemple, ces modèles ne tiennent pas compte de la source de données, ils ne sont pas dotés de mécanismes de traitement sémantique et ils ne tiennent pas compte du passage à l’échelle (en termes de complexité). C'est pourquoi, nous proposons dans cette thèse un modèle d’utilisateur et de source de données basé sur l’analyse d’usage. Les caractéristiques de ce modèle sont les suivantes. Premièrement, il est générique, permettant de représenter à la fois un utilisateur et une source de données. Deuxièmement, il permet de construire le profil de manière implicite à partir de l’historique de requêtes de recherche. Troisièmement, il définit le profil comme un ensemble de centres d’intérêts, chaque intérêt correspondant à un cluster sémantique de mots-clés déterminé par un algorithme de clustering spécifique. Et enfin, dans ce modèle le profil est représenté dans un espace vectoriel. Les différents composants du modèle sont organisés sous la forme d’un Framework, la complexité de chaque composant y est évaluée. Le Framework propose : - une méthode pour la désambigüisation de requêtes; - une méthode pour la représentation sémantique des logs sous la forme d’une taxonomie ; - un algorithme de clustering qui permet l’identification rapide et efficace des centres d’intérêt représentés par des clusters sémantiques de mots clés ; - une méthode pour le calcul du profil de l’utilisateur et du profil de la source de données à partir du modèle générique. Le Framework proposé permet d'effectuer différentes tâches liées à la structuration d’un environnement distribué d’un point de vue usage. Comme exemples d’application, le Framework est utilisé pour la découverte de communautés d’utilisateurs et la catégorisation de sources de données. Pour la validation du Framework, une série d’expérimentations est menée en utilisant des logs du moteur de recherche AOL-search, qui ont démontrées l’efficacité de la désambigüisation sur des requêtes courtes, et qui ont permis d’identification de la relation entre le clustering basé sur une fonction de qualité et le clustering basé sur la structure. / This thesis addresses a problem related to usage analysis in information retrieval systems. Indeed, we exploit the history of search queries as support of analysis to extract a profile model. The objective is to characterize the user and the data source that interact in a system to allow different types of comparison (user-to-user, source-to-source, user-to-source). According to the study we conducted on the work done on profile model, we concluded that the large majority of the contributions are strongly related to the applications within they are proposed. As a result, the proposed profile models are not reusable and suffer from several weaknesses. For instance, these models do not consider the data source, they lack of semantic mechanisms and they do not deal with scalability (in terms of complexity). Therefore, we propose a generic model of user and data source profiles. The characteristics of this model are the following. First, it is generic, being able to represent both the user and the data source. Second, it enables to construct the profiles in an implicit way based on histories of search queries. Third, it defines the profile as a set of topics of interest, each topic corresponding to a semantic cluster of keywords extracted by a specific clustering algorithm. Finally, the profile is represented according to the vector space model. The model is composed of several components organized in the form of a framework, in which we assessed the complexity of each component. The main components of the framework are: - a method for keyword queries disambiguation; - a method for semantically representing search query logs in the form of a taxonomy; - a clustering algorithm that allows fast and efficient identification of topics of interest as semantic clusters of keywords; - a method to identify user and data source profiles according to the generic model. This framework enables in particular to perform various tasks related to usage-based structuration of a distributed environment. As an example of application, the framework is used to the discovery of user communities, and the categorization of data sources. To validate the proposed framework, we conduct a series of experiments on real logs from the search engine AOL search, which demonstrate the efficiency of the disambiguation method in short queries, and show the relation between the quality based clustering and the structure based clustering.

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

The goal of the diploma thesis is to design, implement and evaluate classifiers for automatic classification of semantic patterns of English verbs according to a pattern lexicon that draws on the Corpus Pattern Analysis. We use a pilot collection of 30 sample English verbs as training and test data sets. We employ standard methods of machine learning. In our experiments we use decision trees, k-nearest neighbourghs (kNN), support vector machines (SVM) and Adaboost algorithms. Among other things we concentrate on feature design and selection. We experiment with both morpho-syntactic and semantic features. Our results show that the morpho-syntactic features are the most important for statistically-driven semantic disambiguation. Nevertheless, for some verbs the use of semantic features plays an important role.

People have complex thoughts, and they often express their thoughts with complex sentences using natural languages. This complexity may facilitate efficient communications among the audience with the same knowledge base. But on the other hand, for a different or new audience this composition becomes cumbersome to understand and analyze. Analysis of such compositions using syntactic or semantic measures is a challenging job and defines the base step for natural language processing. In this dissertation I explore and propose a number of new techniques to analyze and visualize the syntactic and semantic patterns of unstructured English texts. The syntactic analysis is done through a proposed visualization technique which categorizes and compares different English compositions based on their different reading complexity metrics. For the semantic analysis I use Latent Semantic Analysis (LSA) to analyze the hidden patterns in complex compositions. I have used this technique to analyze comments from a social visualization web site for detecting the irrelevant ones (e.g., spam). The patterns of collaborations are also studied through statistical analysis. Word sense disambiguation is used to figure out the correct sense of a word in a sentence or composition. Using textual similarity measure, based on the different word similarity measures and word sense disambiguation on collaborative text snippets from social collaborative environment, reveals a direction to untie the knots of complex hidden patterns of collaboration.