Automated classification of texts into genres can benefit NLP applications, in that the structure, location and even interpretation of information within a text are dictated by its genre. Cross-lingual methods promise such benefits to languages which lack genre-annotated training data. While there has been work on genre classification for over two decades, none has considered cross-lingual methods before the start of this project. My research aims to fill this gap. It follows previous approaches to monolingual genre classification that exploit simple, low-level text features, many of which can be extracted in different languages and have similar functions. This contrasts with work on cross-lingual topic or sentiment classification of texts that typically use word frequencies as features. These have been shown to have limited use when it comes to genres. Many such methods also assume cross-lingual resources, such as machine translation, which limits the range of their application. A selection of these approaches are used as baselines in my experiments. I report the results of two semi-supervised methods for exploiting genre-labelled source language texts and unlabelled target language texts. The first is a relatively simple algorithm that bridges the language gap by exploiting cross-lingual features and then iteratively re-trains a classification model on previously predicted target texts. My results show that this approach works well where only few cross-lingual resources are available and texts are to be classified into broad genre categories. It is also shown that further improvements can be achieved through multi-lingual training or cross-lingual feature selection if genre-annotated texts are available in several source languages. The second is a variant of the label propagation algorithm. This graph-based classifier learns genre-specific feature set weights from both source and target language texts and uses them to adjust the propagation channels for each text. This allows further feature sets to be added as additional resources, such as Part of Speech taggers, become available. While the method performs well even with basic text features, it is shown to benefit from additional feature sets. Results also indicate that it handles fine-grained genre classes better than the iterative re-labelling method.

Making computers automatically find the appropriate meaning of words in context is an interesting problem that has proven to be one of the most challenging tasks in natural language processing (NLP). Widespread potential applications of a possible solution to the problem could be envisaged in several NLP tasks such as text simplification, language learning, machine translation, query expansion, information retrieval and text summarization. Ambiguity of words has always been a challenge in these applications, and the traditional endeavor to solve the problem of this ambiguity, namely doing word sense disambiguation using resources like WordNet, has been fraught with debate about the feasibility of the granularity that exists in WordNet senses. The recent trend has therefore been to move away from enforcing any given lexical resource upon automated systems from which to pick potential candidate senses,and to instead encourage them to pick and choose their own resources. Given a sentence with a target ambiguous word, an alternative solution consists of picking potential candidate substitutes for the target, filtering the list of the candidates to a much shorter list using various heuristics, and trying to match these system predictions against a human generated gold standard, with a view to ensuring that the meaning of the sentence does not change after the substitutions. This solution has manifested itself in the SemEval 2007 task of lexical substitution and the more recent SemEval 2010 task of cross-lingual lexical substitution (which I helped organize), where given an English context and a target word within that context, the systems are required to provide between one and ten appropriate substitutes (in English) or translations (in Spanish) for the target word. In this dissertation, I present a comprehensive overview of state-of-the-art research and describe new experiments to tackle the tasks of lexical substitution and cross-lingual lexical substitution. In particular I attempt to answer some research questions pertinent to the tasks, mostly focusing on completely unsupervised approaches. I present a new framework for unsupervised lexical substitution using graphs and centrality algorithms. An additional novelty in this approach is the use of directional similarity rather than the traditional, symmetric word similarity. Additionally, the thesis also explores the extension of the monolingual framework into a cross-lingual one, and examines how well this cross-lingual framework can work for the monolingual lexical substitution and cross-lingual lexical substitution tasks. A comprehensive set of comparative investigations are presented amongst supervised and unsupervised methods, several graph based methods, and the use of monolingual and multilingual information.

No description available.

With the emergence and proliferation of Internet services and e-commerce applications, a tremendous amount of information is accessible online, typically as textual documents. To facilitate subsequent access to and leverage from this information, the efficient and effective management¡Xspecifically, text categorization¡Xof the ever-increasing volume of textual documents is essential to organizations and person. Existing text categorization techniques focus mainly on categorizing monolingual documents. However, with the globalization of business environments and advances in Internet technology, an organization or person often retrieves and archives documents in different languages, thus creating the need for cross-lingual text categorization. Motivated by the significance of and need for such a cross-lingual text categorization technique, this thesis designs a technique with two different category assignment methods, namely, individual- and cluster-based. The empirical evaluation results show that the cross-lingual text categorization technique performs well and the cluster-based method outperforms the individual-based method.

Text categorization deals with the automatic learning of a text categorization model from a training set of preclassified documents on the basis of their contents and the assignment of unclassified documents to appropriate categories. Most of existing text categorization techniques deal with monolingual documents (i.e., all documents are written in one language) during the text categorization model learning and category assignment (or prediction). However, with the globalization of business environments and advances in Internet technology, an organization or individual often generates/acquires and subsequently archives documents in different languages, thus creating the need for cross-lingual text categorization (CLTC). Existing studies on CLTC focus on the prediction-corpus translation-based approach that lacks of a systematic mechanism for reducing translation noises; thus, limiting their cross-lingual categorization effectiveness. Motivated by the needs of providing more effective CLTC support, we design a training-corpus translation-based CLTC approach. Using the prediction-corpus translation-based approach as the performance benchmark, our empirical evaluation results show that our proposed CLTC approach achieves significantly better classification effectiveness than the benchmark approach does in both Chinese

Question answering from a corpus of question-answer (QA) pairs accepts a user question in a natural language, and retrieves relevant QA pairs in the corpus. Most of existing question answering techniques are monolingual in nature. That is, the language used for expressing a user question is identical to that for the QA pairs in the corpus. However, with the globalization of business environments and advances in Internet technology, more and more online information and knowledge are stored in the question-answer pair format on the Internet or intranet in different languages. To facilitate users¡¦ access to these QA-pair documents using natural language queries in such a multilingual environment, there is a pressing need for the support of cross-lingual question answering (CLQA). In response, this study designs a thesaurus based CLQA technique. We empirically evaluate our proposed CLQA technique, using a monolingual question answering technique and a machine translation based CLQA technique as performance benchmarks. Our empirical evaluation results show that our proposed CLQA technique achieves a satisfactory effectiveness when using that of the monolingual question answering technique as a performance reference. Moreover, our empirical evaluation results suggest our proposed thesaurus based CLQA technique significantly outperforms the benchmark machine translation based CLQA technique.

Le Web des données étend le Web en publiant des données structurées et liées en RDF. Un jeu de données RDF est un graphe orienté où les ressources peuvent être des sommets étiquetées dans des langues naturelles. Un des principaux défis est de découvrir les liens entre jeux de données RDF. Étant donnés deux jeux de données, cela consiste à trouver les ressources équivalentes et les lier avec des liens owl:sameAs. Ce problème est particulièrement difficile lorsque les ressources sont décrites dans différentes langues naturelles.Cette thèse étudie l'efficacité des ressources linguistiques pour le liage des données exprimées dans différentes langues. Chaque ressource RDF est représentée comme un document virtuel contenant les informations textuelles des sommets voisins. Les étiquettes des sommets voisins constituent le contexte d'une ressource. Une fois que les documents sont créés, ils sont projetés dans un même espace afin d'être comparés. Ceci peut être réalisé à l'aide de la traduction automatique ou de ressources lexicales multilingues. Une fois que les documents sont dans le même espace, des mesures de similarité sont appliquées afin de trouver les ressources identiques. La similarité entre les documents est prise pour la similarité entre les ressources RDF.Nous évaluons expérimentalement différentes méthodes pour lier les données RDF. En particulier, deux stratégies sont explorées: l'application de la traduction automatique et l'usage des banques de données terminologiques et lexicales multilingues. Dans l'ensemble, l'évaluation montre l'efficacité de ce type d'approches. Les méthodes ont été évaluées sur les ressources en anglais, chinois, français, et allemand. Les meilleurs résultats (F-mesure > 0.90) ont été obtenus par la traduction automatique. L'évaluation montre que la méthode basée sur la similarité peut être appliquée avec succès sur les ressources RDF indépendamment de leur type (entités nommées ou concepts de dictionnaires). / The Semantic Web extends the Web by publishing structured and interlinked data using RDF.An RDF data set is a graph where resources are nodes labelled in natural languages. One of the key challenges of linked data is to be able to discover links across RDF data sets. Given two data sets, equivalent resources should be identified and linked by owl:sameAs links. This problem is particularly difficult when resources are described in different natural languages.This thesis investigates the effectiveness of linguistic resources for interlinking RDF data sets. For this purpose, we introduce a general framework in which each RDF resource is represented as a virtual document containing text information of neighboring nodes. The context of a resource are the labels of the neighboring nodes. Once virtual documents are created, they are projected in the same space in order to be compared. This can be achieved by using machine translation or multilingual lexical resources. Once documents are in the same space, similarity measures to find identical resources are applied. Similarity between elements of this space is taken for similarity between RDF resources.We performed evaluation of cross-lingual techniques within the proposed framework. We experimentally evaluate different methods for linking RDF data. In particular, two strategies are explored: applying machine translation or using references to multilingual resources. Overall, evaluation shows the effectiveness of cross-lingual string-based approaches for linking RDF resources expressed in different languages. The methods have been evaluated on resources in English, Chinese, French and German. The best performance (over 0.90 F-measure) was obtained by the machine translation approach. This shows that the similarity-based method can be successfully applied on RDF resources independently of their type (named entities or thesauri concepts). The best experimental results involving just a pair of languages demonstrated the usefulness of such techniques for interlinking RDF resources cross-lingually.

Computational approaches to linguistic analysis have been used for more than half a century. The main tools come from the field of Natural Language Processing (NLP) and are based on rule-based or corpora-based (supervised) methods. Despite the undeniable success of supervised learning methods in NLP, they have two main drawbacks: on the practical side, it is expensive to produce the manual annotation (or the rules) required and it is not easy to find annotators for less common languages. A theoretical disadvantage is that the computational analysis produced is tied to a specific theory or annotation scheme. Unsupervised methods offer the possibility to expand our analyses into more resourcepoor languages, and to move beyond the conventional linguistic theories. They are a way of observing patterns and regularities emerging directly from the data and can provide new linguistic insights. In this thesis I explore unsupervised methods for inducing parts of speech across languages. I discuss the challenges in evaluation of unsupervised learning and at the same time, by looking at the historical evolution of part-of-speech systems, I make the case that the compartmentalised, traditional pipeline approach of NLP is not ideal for the task. I present a generative Bayesian system that makes it easy to incorporate multiple diverse features, spanning different levels of linguistic structure, like morphology, lexical distribution, syntactic dependencies and word alignment information that allow for the examination of cross-linguistic patterns. I test the system using features provided by unsupervised systems in a pipeline mode (where the output of one system is the input to another) and show that the performance of the baseline (distributional) model increases significantly, reaching and in some cases surpassing the performance of state-of-the-art part-of-speech induction systems. I then turn to the unsupervised systems that provided these sources of information (morphology, dependencies, word alignment) and examine the way that part-of-speech information influences their inference. Having established a bi-directional relationship between each system and my part-of-speech inducer, I describe an iterated learning method, where each component system is trained using the output of the other system in each iteration. The iterated learning method improves the performance of both component systems in each task. Finally, using this iterated learning framework, and by using parts of speech as the central component, I produce chains of linguistic structure induction that combine all the component systems to offer a more holistic view of NLP. To show the potential of this multi-level system, I demonstrate its use ‘in the wild’. I describe the creation of a vastly multilingual parallel corpus based on 100 translations of the Bible in a diverse set of languages. Using the multi-level induction system, I induce cross-lingual clusters, and provide some qualitative results of my approach. I show that it is possible to discover similarities between languages that correspond to ‘hidden’ morphological, syntactic or semantic elements.

A conversão de voz é um problema emergente em processamento de fala e voz com um crescente interesse comercial, tanto em aplicações como Tradução Fala para Fala (Speech-to-Speech Translation - SST) e em sistemas Text-To-Speech (TTS) personalizados. Um sistema de Conversão de Voz deve permitir o mapeamento de características acústicas de sentenças pronunciadas por um falante origem para valores correspondentes da voz do falante destino, de modo que a saída processada é percebida como uma sentença pronunciada pelo falante destino. Nas últimas duas décadas, o número de contribuições cientícas relacionadas ao problema de conversão de voz tem crescido consideravelmente, e um panorama sólido do processo histórico, assim como de técnicas propostas são indispensáveis para contribuição neste campo. O objetivo deste trabalho é realizar um levantamento geral das técnicas utilizadas para resolver o problema, apontando vantagens e desvantagens de cada método, e a partir deste estudo, desenvolver novas ferramentas. Dentre as contribuições do trabalho, foram desenvolvidos um método para decomposição espectral em termos de bases radiais, mapas fonéticos articiais, agrupamentos k-verossímeis, funções de empenamento em frequência entre outras, com o intuito de implementar um sistema de conversão de voz inter-linguístico independente de texto de alta qualidade. / Voice conversion is an emergent problem in voice and speech processing with increasing commercial interest, due to applications such as Speech-to-Speech Translation (SST) and personalized Text-To-Speech (TTS) systems. A Voice Conversion system should allow the mapping of acoustical features of sentences pronounced by a source speaker to values corresponding to the voice of a target speaker, in such a way that the processed output is perceived as a sentence uttered by the target speaker. In the last two decades the number of scientic contributions to the voice conversion problem has grown considerably, and a solid overview of the historical process as well as of the proposed techniques is indispensable for those willing to contribute to the eld. The goal of this work is to provide a critical survey that combines historical presentation to technical discussion while pointing out advantages and drawbacks of each technique, and from this study, to develop new tools. Some contributions proposed in this work include a method for spectral decomposition in terms of radial basis functions, articial phonetic map, warping functions among others, in order to implement a text-independent crosslingual voice conversion system of high quality.

With the emergence of the Internet, many innovative and interesting applications from different countries have been stimulated and e-commerce is also getting more and more pervasive. Under this scenario, tremendous amount of information expressed in different languages are exchanged and shared by not only organizations but also individuals in the modern global environment. A large proportion of information is typically formatted and available as textual documents and managed by using categories. Consequently, the development of a practical and effective technique to deal with the problem of cross-lingual category integration (CLCI) becomes a very essential and important issue. Several category integration techniques have been proposed, but all of them deal with category integration involving only monolingual documents. In response, in this study, we combine the existing cross-lingual text categorization techniques with an existing monolingual category integration technique (specifically, Enhanced Naive Bayes) and proposed a CLCI solution to address cross-lingual category integration. Our empirical evaluation results show that our proposed CLCI technique demonstrates its feasibility and superior effectiveness.