A etiquetagem morfossintática envolve atribuir às palavras de uma sentença suas classes morfossintáticas de acordo com os contextos em que elas aparecem. Cadeias de Markov de Tamanho Variável (VLMCs, do inglês \"Variable-Length Markov Chains\") oferecem uma forma de modelar contextos maiores que trigramas sem sofrer demais com a esparsidade de dados e a complexidade do espaço de estados. Mesmo assim, duas palavras do português apresentam um alto grau de ambiguidade: \'que\' e \'a\'. O número de erros na etiquetagem dessas palavras corresponde a um quarto do total de erros cometidos por um etiquetador baseado em VLMCs. Além disso, essas palavras parecem apresentar dois diferentes tipos de ambiguidade: um dependendo de contexto não local e outro de contexto direito. Exploramos maneiras de expandir o modelo baseado em VLMCs através do uso de diferentes modelos e métodos, a fim de atacar esses problemas. As abordagens mostraram variado grau de sucesso, com um método em particular (aprendizado guiado) se mostrando capaz de resolver boa parte da ambiguidade de \'a\'. Discutimos razões para isso acontecer. Com relação a \'que\', ao longo desta tese propusemos e testamos diversos métodos de aprendizado de informação contextual para tentar desambiguá-lo. Mostramos como, em todos eles, o nível de ambiguidade de \'que\' permanece praticamente constante. / Part-of-speech tagging involves assigning to words in a sentence their part-of-speech class based on the contexts they appear in. Variable-Length Markov Chains (VLMCs) offer a way of modeling contexts longer than trigrams without suffering too much from data sparsity and state space complexity. Even so, two words in Portuguese show a high degree of ambiguity: \'que\' and \'a\'. The number of errors tagging these words corresponds to a quarter of the total errors made by a VLMC-based tagger. Moreover, these words seem to show two different types of ambiguity: one depending on non-local context and one on right context. We searched ways of expanding the VLMC-based model with a number of different models and methods in order to tackle these issues. The approaches showed variable degrees of success, with one particular method (Guided Learning) solving much of the ambiguity of \'a\'. We explore reasons why this happened. Rega rding \'que\', throughout this thesis we propose and test various methods for learning contextual information in order to try to disambiguate it. We show how, in all of them, the level of ambiguity shown by \'que\' remains practically c onstant.

Part-of-speech (POS) tagging is one of the most fundamental and crucial tasks in Natural Language Processing. Chinese POS tagging is challenging because it also involves word segmentation. In this report, research will be focused on how to improve unsupervised Part-of-Speech (POS) tagging using Hidden Markov Models and the Expectation Maximization parameter estimation approach (EM-HMM). The traditional EM-HMM system uses a dictionary, which is used to constrain possible tag sequences and initialize the model parameters. This is a very crude initialization: the emission parameters are set uniformly in accordance with the tag dictionary. To improve this, word alignments can be used. Word alignments are the word-level translation correspondent pairs generated from parallel text between two languages. In this report, Chinese-English word alignment is used. The performance is expected to be better, as these two tasks are complementary to each other. The dictionary provides information on word types, while word alignment provides information on word tokens. However, it is found to be of limited benefit. In this report, another method is proposed. To improve the dictionary coverage and get better POS distribution, Modified Adsorption, a label propagation algorithm is used. We construct a graph connecting word tokens to feature types (such as word unigrams and bigrams) and connecting those tokens to information from knowledge sources, such as a small tag dictionary, Wiktionary, and word alignments. The core idea is to use a small amount of supervision, in the form of a tag dictionary and acquire POS distributions for each word (both known and unknown) and provide this as an improved initialization for EM learning for HMM. We find this strategy to work very well, especially when we have a small tag dictionary. Label propagation provides a better initialization for the EM-HMM method, because it greatly increases the coverage of the dictionary. In addition, label propagation is quite flexible to incorporate many kinds of knowledge. However, results also show that some resources, such as the word alignments, are not easily exploited with label propagation. / text

Any community that wants to be part of technological progress has to ensure that the language(s) of that community has/have the necessary human language technology resources. Part of these resources are so-called "core technologies", including part-of-speech taggers. The first part-of-speech tagger for Afrikaans is developed in this research project. It is indicated that three resources (a tag set, a twig algorithm and annotated training data) are necessary for the development of such a part-of-speech tagger. Since none of these resources exist for Afrikaans, three objectives are formulated for this project, i.e. (a) to develop a linpsticdy accurate tag set for Afrikaans; (b) to deter- mine which algorithm is the most effective one to use; and (c) to find an effective method for generating annotated Afrikaans training data. To reach the first objective, a unique and language-specific tag set was developed for Afrikaans. The resulting tag set is relatively big and consists of 139 tags. The level of specificity of the tag set can easily be adjusted to make the tag set smaller and less specific. After the development of the tag set, research is done on different approaches to, and techniques that can be used in, the development of a part-of-speech tagger. The available algorithms are evaluated by means of prerequisites that were set and in doing so, the most effective algorithm for the purposes of this project, TnT, is identified. Bootstrapping is then used to generate training data with the help of the TnT algorithm. This process results in 20,000 correctly annotated words, and thus annotated training data, the hard resource which is necessary for the development of a part-of-speech tagger, is developed. The tagger that is trained with 20,000 words reaches an accuracy of 85.87% when evaluated. The tag set is then simplified to thirteen tags in order to determine the effect that the size of the tag set has on the accuracy of the tagger. The tagger is 93.69% accurate when using the diminished tag set. The main conclusion of this study is that training data of 20,000 words is not enough for the Afrikaans TnT tagger to compete with other state-of-the-art taggers. The tagger and the data that is developed in this project can be used to generate even more training data in order to develop an optimally accurate Afrikaans TnT tagger. Different techniques might also lead to better results; therefore other algorithms should be tested. / Thesis (M.A.)--North-West University, Potchefstroom Campus, 2005.

This thesis proposes a generalized probabilistic approach to modelling document collections along the combined axes of both semantics and syntax. Probabilistic topic (or semantic) models view documents as random mixtures of unobserved latent topics which are themselves represented as probabilistic distributions over words. They have grown immensely in popularity since the introduction of the original topic model, Latent Dirichlet Allocation (LDA), in 2004, and have seen successes in computational linguistics, bioinformatics, political science, and many other fields. Furthermore, the modular nature of topic models allows them to be extended and adapted to specific tasks with relative ease. Despite the recorded successes, however, there remains a gap in combining axes of information from different sources and in developing models that are as useful as possible for specific applications, particularly in Natural Language Processing (NLP). The main contributions of this thesis are two-fold. First, we present generalized probabilistic models (both parametric and nonparametric) that are semantically and syntactically coherent and contain many simpler probabilistic models as special cases. Our models are consistent along both axes of word information in that an LDA-like component sorts words that are semantically related into distinct topics and a Hidden Markov Model (HMM)-like component determines the syntactic parts-of-speech of words so that we can group words that are both semantically and syntactically affiliated in an unsupervised manner, leading to such groups as verbs about health care and nouns about sports. Second, we apply our generalized probabilistic models to two NLP tasks. Specifically, we present new approaches to automatic text summarization and unsupervised part-of-speech (POS) tagging using our models and report results commensurate with the state-of-the-art in these two sub-fields. Our successes demonstrate the general applicability of our modelling techniques to important areas in computational linguistics and NLP.

This thesis presents open source resources in the form of annotated corpora and modules for automatic morphosyntactic processing and analysis of Persian texts. More specifically, the resources consist of an improved part-of-speech tagged corpus and a dependency treebank, as well as tools for text normalization, sentence segmentation, tokenization, part-of-speech tagging, and dependency parsing for Persian. In developing these resources and tools, two key requirements are observed: compatibility and reuse. The compatibility requirement encompasses two parts. First, the tools in the pipeline should be compatible with each other in such a way that the output of one tool is compatible with the input requirements of the next. Second, the tools should be compatible with the annotated corpora and deliver the same analysis that is found in these. The reuse requirement means that all the components in the pipeline are developed by reusing resources, standard methods, and open source state-of-the-art tools. This is necessary to make the project feasible. Given these requirements, the thesis investigates two main research questions. The first is how can we develop morphologically and syntactically annotated corpora and tools while satisfying the requirements of compatibility and reuse? The approach taken is to accept the tokenization variations in the corpora to achieve robustness. The tokenization variations in Persian texts are related to the orthographic variations of writing fixed expressions, as well as various types of affixes and clitics. Since these variations are inherent properties of Persian texts, it is important that the tools in the pipeline can handle them. Therefore, they should not be trained on idealized data. The second question concerns how accurately we can perform morphological and syntactic analysis for Persian by adapting and applying existing tools to the annotated corpora. The experimental evaluation of the tools shows that the sentence segmenter and tokenizer achieve an F-score close to 100%, the tagger has an accuracy of nearly 97.5%, and the parser achieves a best labeled accuracy of over 82% (with unlabeled accuracy close to 87%).

Any community that wants to be part of technological progress has to ensure that the language(s) of that community has/have the necessary human language technology resources. Part of these resources are so-called "core technologies", including part-of-speech taggers. The first part-of-speech tagger for Afrikaans is developed in this research project. It is indicated that three resources (a tag set, a twig algorithm and annotated training data) are necessary for the development of such a part-of-speech tagger. Since none of these resources exist for Afrikaans, three objectives are formulated for this project, i.e. (a) to develop a linpsticdy accurate tag set for Afrikaans; (b) to deter- mine which algorithm is the most effective one to use; and (c) to find an effective method for generating annotated Afrikaans training data. To reach the first objective, a unique and language-specific tag set was developed for Afrikaans. The resulting tag set is relatively big and consists of 139 tags. The level of specificity of the tag set can easily be adjusted to make the tag set smaller and less specific. After the development of the tag set, research is done on different approaches to, and techniques that can be used in, the development of a part-of-speech tagger. The available algorithms are evaluated by means of prerequisites that were set and in doing so, the most effective algorithm for the purposes of this project, TnT, is identified. Bootstrapping is then used to generate training data with the help of the TnT algorithm. This process results in 20,000 correctly annotated words, and thus annotated training data, the hard resource which is necessary for the development of a part-of-speech tagger, is developed. The tagger that is trained with 20,000 words reaches an accuracy of 85.87% when evaluated. The tag set is then simplified to thirteen tags in order to determine the effect that the size of the tag set has on the accuracy of the tagger. The tagger is 93.69% accurate when using the diminished tag set. The main conclusion of this study is that training data of 20,000 words is not enough for the Afrikaans TnT tagger to compete with other state-of-the-art taggers. The tagger and the data that is developed in this project can be used to generate even more training data in order to develop an optimally accurate Afrikaans TnT tagger. Different techniques might also lead to better results; therefore other algorithms should be tested. / Thesis (M.A.)--North-West University, Potchefstroom Campus, 2005.

The aim of this thesis is to explore the viability of artificial neural networks using a purely contextual word representation as a solution for part-of-speech tagging. Furthermore, the effects of deep learning and increased contextual information of the network are explored. This was achieved by creating an artificial neural network written in Python. The input vectors employed were created by Word2Vec. This system was compared to a baseline using a tagger with handcrafted features in respect to accuracy and precision. The results show that the use of artificial neural networks using a purely contextual word representation shows promise, but ultimately falls roughly two percent short of the baseline. The suspected reason for this is the suboptimal representation for rare words. The use of deeper network architectures shows an insignificant improvement, indicating that the data sets used might be too small. The use of additional context information provided a higher accuracy, but started to decline after a context size of one.

Current research in Natural Language Processing (NLP) tends to exploit corpus resources as a way of overcoming the problem of knowledge acquisition. Statistical analysis of corpora can reveal trends and probabilities of occurrence, which have proved to be helpful in various ways. Machine Translation (MT) is no exception to this trend. Many MT researchers have attempted to extract knowledge from parallel bilingual corpora. The MT problem is generally decomposed into two sub-problems: lexical selection and reordering of the selected words. This research addresses the problem of lexical selection of open-class lexical items in the framework of MT. The work reported in this thesis investigates different methodologies to handle this problem, using a corpus-based approach. The current framework can be applied to any language pair, but we focus on Arabic and English. This is because Arabic words are hugely ambiguous and thus pose a challenge for the current task of lexical selection. We use a challenging Arabic-English parallel corpus, containing many long passages with no punctuation marks to denote sentence boundaries. This points to the robustness of the adopted approach. In our attempt to extract lexical equivalents from the parallel corpus we focus on the co-occurrence relations between words. The current framework adopts a lexicon-free approach towards the selection of lexical equivalents. This has the double advantage of investigating the effectiveness of different techniques without being distracted by the properties of the lexicon and at the same time saving much time and effort, since constructing a lexicon is time-consuming and labour-intensive. Thus, we use as little, if any, hand-coded information as possible. The accuracy score could be improved by adding hand-coded information. The point of the work reported here is to see how well one can do without any such manual intervention. With this goal in mind, we carry out a number of preprocessing steps in our framework. First, we build a lexicon-free Part-of-Speech (POS) tagger for Arabic. This POS tagger uses a combination of rule-based, transformation-based learning (TBL) and probabilistic techniques. Similarly, we use a lexicon-free POS tagger for English. We use the two POS taggers to tag the bi-texts. Second, we develop lexicon-free shallow parsers for Arabic and English. The two parsers are then used to label the parallel corpus with dependency relations (DRs) for some critical constructions. Third, we develop stemmers for Arabic and English, adopting the same knowledge -free approach. These preprocessing steps pave the way for the main system (or proposer) whose task is to extract translational equivalents from the parallel corpus. The framework starts with automatically extracting a bilingual lexicon using unsupervised statistical techniques which exploit the notion of co-occurrence patterns in the parallel corpus. We then choose the target word that has the highest frequency of occurrence from among a number of translational candidates in the extracted lexicon in order to aid the selection of the contextually correct translational equivalent. These experiments are carried out on either raw or POS-tagged texts. Having labelled the bi-texts with DRs, we use them to extract a number of translation seeds to start a number of bootstrapping techniques to improve the proposer. These seeds are used as anchor points to resegment the parallel corpus and start the selection process once again. The final F-score for the selection process is 0.701. We have also written an algorithm for detecting ambiguous words in a translation lexicon and obtained a precision score of 0.89.

A etiquetagem morfossintática envolve atribuir às palavras de uma sentença suas classes morfossintáticas de acordo com os contextos em que elas aparecem. Cadeias de Markov de Tamanho Variável (VLMCs, do inglês \"Variable-Length Markov Chains\") oferecem uma forma de modelar contextos maiores que trigramas sem sofrer demais com a esparsidade de dados e a complexidade do espaço de estados. Mesmo assim, duas palavras do português apresentam um alto grau de ambiguidade: \'que\' e \'a\'. O número de erros na etiquetagem dessas palavras corresponde a um quarto do total de erros cometidos por um etiquetador baseado em VLMCs. Além disso, essas palavras parecem apresentar dois diferentes tipos de ambiguidade: um dependendo de contexto não local e outro de contexto direito. Exploramos maneiras de expandir o modelo baseado em VLMCs através do uso de diferentes modelos e métodos, a fim de atacar esses problemas. As abordagens mostraram variado grau de sucesso, com um método em particular (aprendizado guiado) se mostrando capaz de resolver boa parte da ambiguidade de \'a\'. Discutimos razões para isso acontecer. Com relação a \'que\', ao longo desta tese propusemos e testamos diversos métodos de aprendizado de informação contextual para tentar desambiguá-lo. Mostramos como, em todos eles, o nível de ambiguidade de \'que\' permanece praticamente constante. / Part-of-speech tagging involves assigning to words in a sentence their part-of-speech class based on the contexts they appear in. Variable-Length Markov Chains (VLMCs) offer a way of modeling contexts longer than trigrams without suffering too much from data sparsity and state space complexity. Even so, two words in Portuguese show a high degree of ambiguity: \'que\' and \'a\'. The number of errors tagging these words corresponds to a quarter of the total errors made by a VLMC-based tagger. Moreover, these words seem to show two different types of ambiguity: one depending on non-local context and one on right context. We searched ways of expanding the VLMC-based model with a number of different models and methods in order to tackle these issues. The approaches showed variable degrees of success, with one particular method (Guided Learning) solving much of the ambiguity of \'a\'. We explore reasons why this happened. Rega rding \'que\', throughout this thesis we propose and test various methods for learning contextual information in order to try to disambiguate it. We show how, in all of them, the level of ambiguity shown by \'que\' remains practically c onstant.

No description available.