Este documento apresenta um estudo em nível de mestrado na área de Geração de Língua Natural (GLN), enfocando a questão da variação humana na tarefa de Geração de Expressões de Referência (GER). O trabalho apresenta um levantamento bibliográfico sobre o tema, a criação de dois algoritmos de GER e a construção de um novo córpus de expressões de referência. Modelos computacionais de GER baseados nos algoritmos criados foram implementados em versões que incorporam e não incorporam a variação humana e empregados em uma série de experimentos de GER em sete córpus de expressões de referência. Resultados comprovam a hipótese inicial de que algoritmos de GER que levam em conta a variação humana podem gerar expressões de referência mais próximas a descrições de seres humanos do que algoritmos que não levam esta questão em conta. Além disso, confirmou-se que algoritmos de GER baseados em técnicas de aprendizado de máquina mostram-se superiores a algoritmos de GER consagrados e amplamente utilizados na literatura, como o algoritmo Incremental. / This work concerns a MSc Project in the field of Natural Language Generation (NLG), focusing on the issue of human variation in the Referring Expression Generation task (REG). The study presents a literature review on the topic, the proposal of two REG algorithms and the construction of a new corpus of referring expressions. Based on these algorithms, two REG models are implemented: with and without taking human variation. These models are employed in a series of REG experiments using seven referring expression corpora. Results confirm the initial hypothesis that REG algorithms that take speaker variation into account outperform existing algorithms that generate speaker-independent descriptions. Moreover, the present study confirms that algorithms based on machine learning techniques overperform existing algorithms, as the Dale and Reiter\'s Incremental algorithm.

Este trabalho apresenta um estudo em nível de mestrado na área de Geração de Língua Natural (GLN), enfocando a experimentação na tarefa de Geração de Expressões de Referência (GER). O trabalho apresenta um levantamento bibliográfico sobre o tema, abordando principalmente o modo monólogo e diálogo de realização destes experimentos. Além disso, é apresentado um modelo computacional para a validação automática das descrições produzidas em experimentos de GER, e a sua incorporação em uma ferramenta WEB para realização de experimentos de custo mais baixo, do tipo monólogo, com os benefícios de experimentos do tipo diálogo. O Modelo é avaliado de maneira intrínseca com base em um conjunto de córpus de GER, e de maneira extrínseca em um experimento real com humanos. Resultados comprovam a hipótese inicial de que descrições coletadas em modo monólogo com validação automática das descrições são mais próximas das descrições obtidas em modo diálogo do que as obtidas em modo monólogo / This work concerns a MSc Project in the field of Natural Language Generation (NLG), focusing on the issue of experimentation in the Referring Expression Generation (REG). The study presents a literature review on the topic, distinguishing between monologue and dialogue experiments. Moreover, a computational model for the validation of referring expressions collected in these experiments is presented. The proposed model is embedded in a WEB tool for the design of low-cost monologue experiments with the advantages of dialogue settings. The Model is assessed intrinsically based on a set of GER corpus, and extrinsically in a real experiment with humans. Results confirm the initial hypothesis that descriptions collected in monologue settings with automatic validation of the descriptions are closer to the descriptions obtained in dialog ones than those obtained in monologue settings

Este documento apresenta uma pesquisa a nvel de mestrado acadêmico, cujo o foco é a tarefa computacional de Geração de Expressões de Referência (GER), uma parte fundamental da comunicação que é estudada na Geração de Linguagem Natural (GLN). Mais especificamente, foram estudados os aspectos da linguagem que se manifestam em contextos de comunicação com restrição de tempo, e com base nisso foi proposto um modelo computacional de GER para produzir expressões de referência com o nvel de superespecificação parametrizável. Além disso, considerando-se as caractersticas de adaptabilidade do modelo proposto, também foi sugerida uma generalização deste para outros domnios, como os que compreendem contextos de comunicação além dos que possuem restrição de tempo / This document presents a MSc research that focused on the computational subtask of Referring Expression Generation (REG), an important component of Natural Language Generation (NLG) systems. More specifically, this work analyzes how time-restricted contexts of communication may affect language production and a computational model of GER was proposed to produce reference expressions with parameterizable superspecification. Furthermore, given the adaptability characteristics of the proposed model, it has also been suggested a generalization to other domains, which includes communication contexts besides those that have time constraints

Sentiment analysis is a field of computational linguistics involving identification, extraction, and classification of opinions, sentiments, and emotions expressed in natural language. Sentiment classification algorithms aim to identify whether the author of a text has a positive or a negative opinion about a topic. One of the main indicators which help to detect the opinion are the words used in the texts. Needless to say, the sentiments expressed in the texts also depend on the syntactic structure and the discourse context. Supervised machine learning approaches to sentiment classification were shown to achieve good results. Classifying texts by emotions requires finer-grained analysis than sentiment classification. In this thesis, we explore the task of emotion and mood classification for blog postings. We propose a novel approach that uses the hierarchy of possible moods to achieve better results than a standard flat classification approach. We also show that using sentiment orientation features improves the performance of classification. We used the LiveJournal blog corpus as a dataset to train and evaluate our method. Another contribution of this work is extracting paraphrases for emotion terms based on the six basics emotions proposed by Ekman (\textit{happiness, anger, sadness, disgust, surprise, fear}). Paraphrases are different ways to express the same information. Algorithms to extract and automatically identify paraphrases are of interest from both linguistic and practical points of view. Our paraphrase extraction method is based on a bootstrapping algorithms that starts with seed words. Unlike in previous work, our algorithm does not need a parallel corpus. In Natural Language Generation (NLG), paraphrasing is employed to create more varied and natural text. In our research, we extract paraphrases for emotions, with the goal of using them to automatically generate emotional texts (such as friendly or hostile texts) for conversations between intelligent agents and characters in educational games. Nowadays, online services are popular in many disciplines such as: e-learning, interactive games, educational games, stock market, chat rooms and so on. NLG methods can be used in order to generate more interesting and normal texts for such applications. Generating text with emotions is one of the contributions of our work. In the last part of this thesis, we give an overview of NLG from an applied system's points of view. We discuss when NLG techniques can be used; we explained the requirements analysis and specification of NLG systems. We also, describe the main NLG tasks of content determination, discourse planning, sentence aggregation, lexicalization, referring expression generation, and linguistic realisation. Moreover, we describe our Authoring Tool that we developed in order to allow writers without programming skills to automatically generate texts for educational games. We develop an NLG system that can generate text with different emotions. To do this, we introduce our pattern-based model for generation. We show our model starts with initial patterns, then constructs extended patterns from which we choose ``final'' patterns that are suitable for generating emotion sentences. A user can generate sentences to express the desired emotions by using our patterns. Alternatively, the user can use our Authoring Tool to generate sentences with emotions. Our acquired paraphrases will be employed by the tool in order to generate more varied outputs.

Sentiment analysis is a field of computational linguistics involving identification, extraction, and classification of opinions, sentiments, and emotions expressed in natural language. Sentiment classification algorithms aim to identify whether the author of a text has a positive or a negative opinion about a topic. One of the main indicators which help to detect the opinion are the words used in the texts. Needless to say, the sentiments expressed in the texts also depend on the syntactic structure and the discourse context. Supervised machine learning approaches to sentiment classification were shown to achieve good results. Classifying texts by emotions requires finer-grained analysis than sentiment classification. In this thesis, we explore the task of emotion and mood classification for blog postings. We propose a novel approach that uses the hierarchy of possible moods to achieve better results than a standard flat classification approach. We also show that using sentiment orientation features improves the performance of classification. We used the LiveJournal blog corpus as a dataset to train and evaluate our method. Another contribution of this work is extracting paraphrases for emotion terms based on the six basics emotions proposed by Ekman (\textit{happiness, anger, sadness, disgust, surprise, fear}). Paraphrases are different ways to express the same information. Algorithms to extract and automatically identify paraphrases are of interest from both linguistic and practical points of view. Our paraphrase extraction method is based on a bootstrapping algorithms that starts with seed words. Unlike in previous work, our algorithm does not need a parallel corpus. In Natural Language Generation (NLG), paraphrasing is employed to create more varied and natural text. In our research, we extract paraphrases for emotions, with the goal of using them to automatically generate emotional texts (such as friendly or hostile texts) for conversations between intelligent agents and characters in educational games. Nowadays, online services are popular in many disciplines such as: e-learning, interactive games, educational games, stock market, chat rooms and so on. NLG methods can be used in order to generate more interesting and normal texts for such applications. Generating text with emotions is one of the contributions of our work. In the last part of this thesis, we give an overview of NLG from an applied system's points of view. We discuss when NLG techniques can be used; we explained the requirements analysis and specification of NLG systems. We also, describe the main NLG tasks of content determination, discourse planning, sentence aggregation, lexicalization, referring expression generation, and linguistic realisation. Moreover, we describe our Authoring Tool that we developed in order to allow writers without programming skills to automatically generate texts for educational games. We develop an NLG system that can generate text with different emotions. To do this, we introduce our pattern-based model for generation. We show our model starts with initial patterns, then constructs extended patterns from which we choose ``final'' patterns that are suitable for generating emotion sentences. A user can generate sentences to express the desired emotions by using our patterns. Alternatively, the user can use our Authoring Tool to generate sentences with emotions. Our acquired paraphrases will be employed by the tool in order to generate more varied outputs.

Sentiment analysis is a field of computational linguistics involving identification, extraction, and classification of opinions, sentiments, and emotions expressed in natural language. Sentiment classification algorithms aim to identify whether the author of a text has a positive or a negative opinion about a topic. One of the main indicators which help to detect the opinion are the words used in the texts. Needless to say, the sentiments expressed in the texts also depend on the syntactic structure and the discourse context. Supervised machine learning approaches to sentiment classification were shown to achieve good results. Classifying texts by emotions requires finer-grained analysis than sentiment classification. In this thesis, we explore the task of emotion and mood classification for blog postings. We propose a novel approach that uses the hierarchy of possible moods to achieve better results than a standard flat classification approach. We also show that using sentiment orientation features improves the performance of classification. We used the LiveJournal blog corpus as a dataset to train and evaluate our method. Another contribution of this work is extracting paraphrases for emotion terms based on the six basics emotions proposed by Ekman (\textit{happiness, anger, sadness, disgust, surprise, fear}). Paraphrases are different ways to express the same information. Algorithms to extract and automatically identify paraphrases are of interest from both linguistic and practical points of view. Our paraphrase extraction method is based on a bootstrapping algorithms that starts with seed words. Unlike in previous work, our algorithm does not need a parallel corpus. In Natural Language Generation (NLG), paraphrasing is employed to create more varied and natural text. In our research, we extract paraphrases for emotions, with the goal of using them to automatically generate emotional texts (such as friendly or hostile texts) for conversations between intelligent agents and characters in educational games. Nowadays, online services are popular in many disciplines such as: e-learning, interactive games, educational games, stock market, chat rooms and so on. NLG methods can be used in order to generate more interesting and normal texts for such applications. Generating text with emotions is one of the contributions of our work. In the last part of this thesis, we give an overview of NLG from an applied system's points of view. We discuss when NLG techniques can be used; we explained the requirements analysis and specification of NLG systems. We also, describe the main NLG tasks of content determination, discourse planning, sentence aggregation, lexicalization, referring expression generation, and linguistic realisation. Moreover, we describe our Authoring Tool that we developed in order to allow writers without programming skills to automatically generate texts for educational games. We develop an NLG system that can generate text with different emotions. To do this, we introduce our pattern-based model for generation. We show our model starts with initial patterns, then constructs extended patterns from which we choose ``final'' patterns that are suitable for generating emotion sentences. A user can generate sentences to express the desired emotions by using our patterns. Alternatively, the user can use our Authoring Tool to generate sentences with emotions. Our acquired paraphrases will be employed by the tool in order to generate more varied outputs.

The relatively recently proposed hierarchical phrase-based translation model for statistical machine translation (SMT) has achieved state-of-the-art performance in numerous recent translation evaluations. Hierarchical phrase-based systems comprise a pipeline of modules with complex interactions. In this thesis, we propose refinements to the hierarchical phrase-based model as well as improvements and analyses in various modules for hierarchical phrase-based systems. We took the opportunity of increasing amounts of available training data for machine translation as well as existing frameworks for distributed computing in order to build better infrastructure for extraction, estimation and retrieval of hierarchical phrase-based grammars. We design and implement grammar extraction as a series of Hadoop MapReduce jobs. We store the resulting grammar using the HFile format, which offers competitive trade-offs in terms of efficiency and simplicity. We demonstrate improvements over two alternative solutions used in machine translation. The modular nature of the SMT pipeline, while allowing individual improvements, has the disadvantage that errors committed by one module are propagated to the next. This thesis alleviates this issue between the word alignment module and the grammar extraction and estimation module by considering richer statistics from word alignment models in extraction. We use alignment link and alignment phrase pair posterior probabilities for grammar extraction and estimation and demonstrate translation improvements in Chinese to English translation. This thesis also proposes refinements in grammar and language modelling both in the context of domain adaptation and in the context of the interaction between first-pass decoding and lattice rescoring. We analyse alternative strategies for grammar and language model cross-domain adaptation. We also study interactions between first-pass and second-pass language model in terms of size and n-gram order. Finally, we analyse two smoothing methods for large 5-gram language model rescoring. The last two chapters are devoted to the application of phrase-based grammars to the string regeneration task, which we consider as a means to study the fluency of machine translation output. We design and implement a monolingual phrase-based decoder for string regeneration and achieve state-of-the-art performance on this task. By applying our decoder to the output of a hierarchical phrase-based translation system, we are able to recover the same level of translation quality as the translation system.

Sentiment analysis is a field of computational linguistics involving identification, extraction, and classification of opinions, sentiments, and emotions expressed in natural language. Sentiment classification algorithms aim to identify whether the author of a text has a positive or a negative opinion about a topic. One of the main indicators which help to detect the opinion are the words used in the texts. Needless to say, the sentiments expressed in the texts also depend on the syntactic structure and the discourse context. Supervised machine learning approaches to sentiment classification were shown to achieve good results. Classifying texts by emotions requires finer-grained analysis than sentiment classification. In this thesis, we explore the task of emotion and mood classification for blog postings. We propose a novel approach that uses the hierarchy of possible moods to achieve better results than a standard flat classification approach. We also show that using sentiment orientation features improves the performance of classification. We used the LiveJournal blog corpus as a dataset to train and evaluate our method. Another contribution of this work is extracting paraphrases for emotion terms based on the six basics emotions proposed by Ekman (\textit{happiness, anger, sadness, disgust, surprise, fear}). Paraphrases are different ways to express the same information. Algorithms to extract and automatically identify paraphrases are of interest from both linguistic and practical points of view. Our paraphrase extraction method is based on a bootstrapping algorithms that starts with seed words. Unlike in previous work, our algorithm does not need a parallel corpus. In Natural Language Generation (NLG), paraphrasing is employed to create more varied and natural text. In our research, we extract paraphrases for emotions, with the goal of using them to automatically generate emotional texts (such as friendly or hostile texts) for conversations between intelligent agents and characters in educational games. Nowadays, online services are popular in many disciplines such as: e-learning, interactive games, educational games, stock market, chat rooms and so on. NLG methods can be used in order to generate more interesting and normal texts for such applications. Generating text with emotions is one of the contributions of our work. In the last part of this thesis, we give an overview of NLG from an applied system's points of view. We discuss when NLG techniques can be used; we explained the requirements analysis and specification of NLG systems. We also, describe the main NLG tasks of content determination, discourse planning, sentence aggregation, lexicalization, referring expression generation, and linguistic realisation. Moreover, we describe our Authoring Tool that we developed in order to allow writers without programming skills to automatically generate texts for educational games. We develop an NLG system that can generate text with different emotions. To do this, we introduce our pattern-based model for generation. We show our model starts with initial patterns, then constructs extended patterns from which we choose ``final'' patterns that are suitable for generating emotion sentences. A user can generate sentences to express the desired emotions by using our patterns. Alternatively, the user can use our Authoring Tool to generate sentences with emotions. Our acquired paraphrases will be employed by the tool in order to generate more varied outputs.

No description available.

No description available.