Natural Language Generation and generating believable verbal communication are critical components in the development of social robots. The work presented in this paper is based on the sequence-to-sequence model and is focused on improving context and repeatability through the inclusion of task- specific information. The data set on which this study was conducted was collected through a Wizard of Oz framework using a social robot. The generated dialogue was evaluated through a survey designed to measure the adherence to the game context and perceived human qualities. The human qualities were measured using attributes from two well-known attribute scales intended for evaluating Human-Robot Interaction. The evaluation results indicate that the quality of the generated dialogue is on par with examples of actual dialogue spoken during the experiments. This paper also highlights interesting aspects regarding the usefulness of transfer learning in narrow contextual applications. The results presented in this paper show that it is possible to improve the contextual nature of generated dialogue by including additional task-specific information. / Generering av naturligt språk och uppgiften att skapa trovärdig verbal kommunikation är kritiska komponenter i utvecklingen av sociala robotar. Arbetet som presenteras i denna uppsats är baserat på sekvens-till-sekvens-modellen och fokuserar på att förbättra sammanhang och repeterbarhet genom att inkludera uppgiftspecifik information. Datauppsättningen som denna studie genomförde samlades in via ett Wizard of Oz-ramverk med hjälp av en social robot. Den genererade dialogen utvärderades genom en onlineundersökning utformad för att mäta efterlevnaden av spelskontexten och upplevda mänskliga egenskaper. Dessa mänskliga egenskaper mättes med attribut från två välkända attributskalor avsedda för utvärdering av människa-robot-interaktion. Utvärderingsresultaten visar att kvaliteten på den genererade dialogen är i nivå med exempel på faktisk dialog som talats under experimenten. Denna uppsats belyser också intressanta aspekter beträffande nyttan av överföringsinlärning i smala kontextuella applikationer. Resultaten som presenteras i denna uppsats visar att det är möjligt att förbättra den kontextuella karaktären hos genererad dialog genom att inkludera ytterligare uppgiftspecifik information.

La génération automatique de texte (GAT) produit du texte en langue naturelle destiné aux humains à partir de données non langagières. L’objectif de la GAT est de concevoir des générateurs réutilisables d’une langue à l’autre et d’une application à l’autre. Pour ce faire, l’architecture des générateurs automatiques de texte est modulaire : on distingue entre la génération profonde qui détermine le contenu du message à exprimer et la réalisation linguistique qui génère les unités et structures linguistiques exprimant le message. La réalisation linguistique multilingue nécessite de modéliser les principaux phénomènes linguistiques de la manière la plus générique possible. Or, les collocations représentent un de ces principaux phénomènes linguistiques et demeurent problématiques en GAT, mais aussi pour le Traitement Automatique des Langues en général. La Théorie Sens-Texte analyse les collocations comme des contraintes de sélection lexicale. Autrement dit, une collocation est composée de trois éléments : (i) la base, (ii) le collocatif, choisi en fonction de la base et (iii) d’une relation sémantico-lexicale. Il existe des relations sémantico-lexicales récurrentes et systématiques. Les fonctions lexicales modélisent ces relations. En effet, des collocations telles que peur bleue ou pluie torrentielle instancient une même relation, l’intensification, que l’on peut décrire au moyen de la fonction lexicale Magn : Magn(PEUR) = BLEUE, Magn(PLUIE) = TORRENTIELLE, etc. Il existe des centaines de fonctions lexicales. Ce mémoire présente la méthodologie d’implémentation des collocations dans un réalisateur de texte multilingue, GÉCO, à l’aide des fonctions lexicales standard syntagmatiques simples et complexes. Le cœur de la méthodologie repose sur le regroupement des fonctions lexicales ayant un fonctionnement similaire dans des patrons génériques. Au total, plus de 26 000 fonctions lexicales ont été implémentées, représentant de ce fait une avancée considérable pour le traitement des collocations en réalisation de texte multilingue. / Natural Language Generation (NLG) produces text in natural language from non-linguistic content. NLG aims at developing generators that are reusable across languages and applications. In order to do so, these systems’ architecture is modular: while the deep generation module determines the content of the message to be expressed, the text realization module maps the message into its most appropriate linguistic form. Multilingual text realization requires to model the core linguistic phenomena that one finds in language. Collocations represent one of the core linguistic phenomena that remain problematic not only in NLG, but also in Natural Language Processing in general. The Meaning-Text theory analyses collocations as constraints on lexical selection. In other words, a collocation is made up of three constituents: (i) the base, (ii) the collocate, chosen according to (iii) a semantico-lexical relation. Some of these semantico-lexical relations are systematic and shared by many collocations. Lexical functions are a system for modeling these relations. In fact, collocations such as heavy rain or strong preference instantiate the same relation, intensity, can be described with the lexical function Magn: Magn(RAIN) = HEAVY, Magn(PREFERENCE) = STRONG, etc. There are hundreds of lexical functions. Our work presents a methodology for the implementation of collocations in a multilingual text realization engine, GÉCO, that relies on simple and complex syntagmatic standard lexical functions. The principal aspect of the methodology consists of regrouping lexical functions that show a similar behavior into generic patterns. As a result, 26 000 lexical functions have been implemented, which is a considerable progress in the treatment of collocations in multilingual text realization.

Cette thèse présente le résultat de plusieurs années de recherche dans le domaine de la génération automatique de résumés. Trois contributions majeures, présentées sous la forme d'articles publiés ou soumis pour publication, en forment le coeur. Elles retracent un cheminement qui part des méthodes par extraction en résumé jusqu'aux méthodes par abstraction. L'expérience HexTac, sujet du premier article, a d'abord été menée pour évaluer le niveau de performance des êtres humains dans la rédaction de résumés par extraction de phrases. Les résultats montrent un écart important entre la performance humaine sous la contrainte d'extraire des phrases du texte source par rapport à la rédaction de résumés sans contrainte. Cette limite à la rédaction de résumés par extraction de phrases, observée empiriquement, démontre l'intérêt de développer d'autres approches automatiques pour le résumé. Nous avons ensuite développé un premier système selon l'approche Fully Abstractive Summarization, qui se situe dans la catégorie des approches semi-extractives, comme la compression de phrases et la fusion de phrases. Le développement et l'évaluation du système, décrits dans le second article, ont permis de constater le grand défi de générer un résumé facile à lire sans faire de l'extraction de phrases. Dans cette approche, le niveau de compréhension du contenu du texte source demeure insuffisant pour guider le processus de sélection du contenu pour le résumé, comme dans les approches par extraction de phrases. Enfin, l'approche par abstraction basée sur des connaissances nommée K-BABS est proposée dans un troisième article. Un repérage des éléments d'information pertinents est effectué, menant directement à la génération de phrases pour le résumé. Cette approche a été implémentée dans le système ABSUM, qui produit des résumés très courts mais riches en contenu. Ils ont été évalués selon les standards d'aujourd'hui et cette évaluation montre que des résumés hybrides formés à la fois de la sortie d'ABSUM et de phrases extraites ont un contenu informatif significativement plus élevé qu'un système provenant de l'état de l'art en extraction de phrases. / This Ph.D. thesis is the result of several years of research on automatic text summarization. Three major contributions are presented in the form of published and submitted papers. They follow a path that moves away from extractive summarization and toward abstractive summarization. The first article describes the HexTac experiment, which was conducted to evaluate the performance of humans summarizing text by extracting sentences. Results show a wide gap of performance between human summaries written by sentence extraction and those written without restriction. This empirical performance ceiling to sentence extraction demonstrates the need for new approaches to text summarization. We then developed and implemented a system, which is the subject of the second article, using the Fully Abstractive Summarization approach. Though the name suggests otherwise, this approach is better categorized as semi-extractive, along with sentence compression and sentence fusion. Building and evaluating this system brought to light the great challenge associated with generating easily readable summaries without extracting sentences. In this approach, text understanding is not deep enough to provide help in the content selection process, as is the case in extractive summarization. As the third contribution, a knowledge-based approach to abstractive summarization called K-BABS was proposed. Relevant content is identified by pattern matching on an analysis of the source text, and rules are applied to directly generate sentences for the summary. This approach is implemented in a system called ABSUM, which generates very short and content-rich summaries. An evaluation was performed according to today's standards. The evaluation shows that hybrid summaries generated by adding extracted sentences to ABSUM's output have significantly more content than a state-of-the-art extractive summarizer.

[pt] Nesta dissertação é estudado o problema de geração e narração de estórias, cuja relevância tem sido cada vez mais reconhecida, principalmente em decorrência da popularização de meios de comunicação interativos, tais como a TV digital e os jogos digitais. O trabalho partiu de uma revisão do estado da arte, destacando os principais modelos para representação de estórias e as técnicas mais utilizadas na criação de obras literárias. Foi proposto o uso do termo engenharia de estórias para enfatizar que a tarefa de geração e narração de estórias deve ser encarada como um processo de engenharia. O problema fundamental foi dividido em três subproblemas. O primeiro diz respeito a como gerar as estórias, o segundo a como contá-las ao público e o último é sobre como construir, armazenar e consultar a base de conhecimento usada na engenharia de estórias. Por fim, como estudo de caso, foi projetado e programado um protótipo capaz de gerar e narrar estórias automaticamente. A geração é efetuada por um planejador, usando o algoritmo de Redes de Tarefas Hierárquicas. Para a narração, é utilizado um gerador de textos em linguagem natural. A base de conhecimento é armazenada na forma de documentos XML tendo sido implementada uma ferramenta para facilitar sua preparação. / [en] This dissertation investigates the problem of story telling and generation, whose increasingly recognized relevance is mostly due to the popularization of interactive media, such as digital TV and video-games. The work initiates with a state of the art survey, detailing the major story representation models and the most used methods in literary work production. The use of the term story engineering was proposed to emphasize that story telling and generation should be viewed as an engineering process. The fundamental problem was divided into three subproblems. The first one is how to generate stories, the second is how to tell them to the public and the last is how to create, store and query the knowledge base used for story engineering. Finally, as a case study, a prototype capable of automatically generating and telling stories was designed and programmed. Generation is done by a planner, using the Hierarchical Task Network algorithm. Storytelling applies a natural language generation tool. The knowledge base is stored under the form ofXMLdocuments, and a tool was implemented to simplify their preparation.

A Geração de Língua Natural (GLN) ocupa-se de atribuir forma lingüística a dados em representação não-lingüística (Reiter & Dale, 2000); a Realização Lingüística (RL), por sua vez, reúne as subtarefas da GLN estritamente dependentes das especificidades da língua-alvo. Este trabalho objetiva a investigação em RL, uma de cujas aplicações mais proeminentes é a construção de módulos geradores de língua-alvo na tradução automática baseada em transferência semântica. Partimos da identificação de três requisitos fundamentais para modelos de RL quais sejam generalidade, instanciabilidade e complexidade e da tensão entre esses requisitos no estado da arte. Argumentamos pela relevância da avaliação formal dos modelos da literatura contra esses critérios e focalizamos em modelos baseados em restrições (Schulte, 2002) como promissores para reconciliar os três requisitos. Nesta classe de modelos, identificamos o recente modelo de Debusmann (2006) Extensible Dependency Grammar (XDG) e sua implementação - o XDG Development Toolkit (XDK) - como uma plataforma especialmente promissora para o desenvolvimento em RL, apesar de jamais utilizada para tal. Nossas contribuições práticas se resumem ao esforço de tornar o XDK mais eficiente e uma formulação da disjunção inerente à lexicalização adequada à XDG, demonstrando suas potenciais vantagens numa sistema de GLN mais completo / Natural Language Generation (NLG) concerns assigning linguistic form to data in nonlinguistic representation (Reiter & Dale, 2000); Linguistic Realization (LR), in turn, comprises all strictly target language-dependent NLG tasks. This work looks into RL systems from the perspective of three fundamental requirements - namely generality, instantiability, and complexity and the tension between them in the state of the art. We argue for the formal evaluation of models against these criteria and focus on constraint-based models (Schulte, 2002) as tools to reconcile them. In this class of models we identify the recent development of Debusmann (2006) - Extensible Dependency Grammar (XDG) - and its implementation - the XDG Development Toolkit (XDK) - as an especially promising platform for RL work, in spite of never having been used as such. Our practical contributions comprehend a successful effort to make the XDK more efficient and a formulation of lexicalization disjunction suitable to XDG, illustrating its potential advantages in a full-fledged NLG system

Cette thèse présente le résultat de plusieurs années de recherche dans le domaine de la génération automatique de résumés. Trois contributions majeures, présentées sous la forme d'articles publiés ou soumis pour publication, en forment le coeur. Elles retracent un cheminement qui part des méthodes par extraction en résumé jusqu'aux méthodes par abstraction. L'expérience HexTac, sujet du premier article, a d'abord été menée pour évaluer le niveau de performance des êtres humains dans la rédaction de résumés par extraction de phrases. Les résultats montrent un écart important entre la performance humaine sous la contrainte d'extraire des phrases du texte source par rapport à la rédaction de résumés sans contrainte. Cette limite à la rédaction de résumés par extraction de phrases, observée empiriquement, démontre l'intérêt de développer d'autres approches automatiques pour le résumé. Nous avons ensuite développé un premier système selon l'approche Fully Abstractive Summarization, qui se situe dans la catégorie des approches semi-extractives, comme la compression de phrases et la fusion de phrases. Le développement et l'évaluation du système, décrits dans le second article, ont permis de constater le grand défi de générer un résumé facile à lire sans faire de l'extraction de phrases. Dans cette approche, le niveau de compréhension du contenu du texte source demeure insuffisant pour guider le processus de sélection du contenu pour le résumé, comme dans les approches par extraction de phrases. Enfin, l'approche par abstraction basée sur des connaissances nommée K-BABS est proposée dans un troisième article. Un repérage des éléments d'information pertinents est effectué, menant directement à la génération de phrases pour le résumé. Cette approche a été implémentée dans le système ABSUM, qui produit des résumés très courts mais riches en contenu. Ils ont été évalués selon les standards d'aujourd'hui et cette évaluation montre que des résumés hybrides formés à la fois de la sortie d'ABSUM et de phrases extraites ont un contenu informatif significativement plus élevé qu'un système provenant de l'état de l'art en extraction de phrases. / This Ph.D. thesis is the result of several years of research on automatic text summarization. Three major contributions are presented in the form of published and submitted papers. They follow a path that moves away from extractive summarization and toward abstractive summarization. The first article describes the HexTac experiment, which was conducted to evaluate the performance of humans summarizing text by extracting sentences. Results show a wide gap of performance between human summaries written by sentence extraction and those written without restriction. This empirical performance ceiling to sentence extraction demonstrates the need for new approaches to text summarization. We then developed and implemented a system, which is the subject of the second article, using the Fully Abstractive Summarization approach. Though the name suggests otherwise, this approach is better categorized as semi-extractive, along with sentence compression and sentence fusion. Building and evaluating this system brought to light the great challenge associated with generating easily readable summaries without extracting sentences. In this approach, text understanding is not deep enough to provide help in the content selection process, as is the case in extractive summarization. As the third contribution, a knowledge-based approach to abstractive summarization called K-BABS was proposed. Relevant content is identified by pattern matching on an analysis of the source text, and rules are applied to directly generate sentences for the summary. This approach is implemented in a system called ABSUM, which generates very short and content-rich summaries. An evaluation was performed according to today's standards. The evaluation shows that hybrid summaries generated by adding extracted sentences to ABSUM's output have significantly more content than a state-of-the-art extractive summarizer.

No description available.

Language is the principal medium for ideas, while dialogue is the most natural and effective way for humans to interact with and access information from machines. Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact on usability and perceived quality. Many commonly used NLG systems employ rules and heuristics, which tend to generate inflexible and stylised responses without the natural variation of human language. However, the frequent repetition of identical output forms can quickly make dialogue become tedious for most real-world users. Additionally, these rules and heuristics are not scalable and hence not trivially extensible to other domains or languages. A statistical approach to language generation can learn language decisions directly from data without relying on hand-coded rules or heuristics, which brings scalability and flexibility to NLG. Statistical models also provide an opportunity to learn in-domain human colloquialisms and cross-domain model adaptations. A robust and quasi-supervised NLG model is proposed in this thesis. The model leverages a Recurrent Neural Network (RNN)-based surface realiser and a gating mechanism applied to input semantics. The model is motivated by the Long-Short Term Memory (LSTM) network. The RNN-based surface realiser and gating mechanism use a neural network to learn end-to-end language generation decisions from input dialogue act and sentence pairs; it also integrates sentence planning and surface realisation into a single optimisation problem. The single optimisation not only bypasses the costly intermediate linguistic annotations but also generates more natural and human-like responses. Furthermore, a domain adaptation study shows that the proposed model can be readily adapted and extended to new dialogue domains via a proposed recipe. Continuing the success of end-to-end learning, the second part of the thesis speculates on building an end-to-end dialogue system by framing it as a conditional generation problem. The proposed model encapsulates a belief tracker with a minimal state representation and a generator that takes the dialogue context to produce responses. These features suggest comprehension and fast learning. The proposed model is capable of understanding requests and accomplishing tasks after training on only a few hundred human-human dialogues. A complementary Wizard-of-Oz data collection method is also introduced to facilitate the collection of human-human conversations from online workers. The results demonstrate that the proposed model can talk to human judges naturally, without any difficulty, for a sample application domain. In addition, the results also suggest that the introduction of a stochastic latent variable can help the system model intrinsic variation in communicative intention much better.

A Geração de Língua Natural (GLN) ocupa-se de atribuir forma lingüística a dados em representação não-lingüística (Reiter & Dale, 2000); a Realização Lingüística (RL), por sua vez, reúne as subtarefas da GLN estritamente dependentes das especificidades da língua-alvo. Este trabalho objetiva a investigação em RL, uma de cujas aplicações mais proeminentes é a construção de módulos geradores de língua-alvo na tradução automática baseada em transferência semântica. Partimos da identificação de três requisitos fundamentais para modelos de RL quais sejam generalidade, instanciabilidade e complexidade e da tensão entre esses requisitos no estado da arte. Argumentamos pela relevância da avaliação formal dos modelos da literatura contra esses critérios e focalizamos em modelos baseados em restrições (Schulte, 2002) como promissores para reconciliar os três requisitos. Nesta classe de modelos, identificamos o recente modelo de Debusmann (2006) Extensible Dependency Grammar (XDG) e sua implementação - o XDG Development Toolkit (XDK) - como uma plataforma especialmente promissora para o desenvolvimento em RL, apesar de jamais utilizada para tal. Nossas contribuições práticas se resumem ao esforço de tornar o XDK mais eficiente e uma formulação da disjunção inerente à lexicalização adequada à XDG, demonstrando suas potenciais vantagens numa sistema de GLN mais completo / Natural Language Generation (NLG) concerns assigning linguistic form to data in nonlinguistic representation (Reiter & Dale, 2000); Linguistic Realization (LR), in turn, comprises all strictly target language-dependent NLG tasks. This work looks into RL systems from the perspective of three fundamental requirements - namely generality, instantiability, and complexity and the tension between them in the state of the art. We argue for the formal evaluation of models against these criteria and focus on constraint-based models (Schulte, 2002) as tools to reconcile them. In this class of models we identify the recent development of Debusmann (2006) - Extensible Dependency Grammar (XDG) - and its implementation - the XDG Development Toolkit (XDK) - as an especially promising platform for RL work, in spite of never having been used as such. Our practical contributions comprehend a successful effort to make the XDK more efficient and a formulation of lexicalization disjunction suitable to XDG, illustrating its potential advantages in a full-fledged NLG system

Formality Style Transfer (FST) is the task of automatically transforming a piece of text from one level of formality to another. Previous research has investigated different methods of performing FST on text in English, but at the time of this project there were to the author’s knowledge no previous studies analysing the quality of FST on text in Swedish. The purpose of this thesis was to investigate how a model trained for FST in Swedish performs. This was done by comparing the quality of a model trained on text in Swedish for FST, to an equivalent model trained on text in English for FST. Both models were implemented as encoder-decoder architectures, warm-started using two pre-existing Bidirectional Encoder Representations from Transformers (BERT) models, pre-trained on Swedish and English text respectively. The two FST models were fine-tuned for both the informal to formal task as well as the formal to informal task, using the Grammarly’s Yahoo Answers Formality Corpus (GYAFC). The Swedish version of GYAFC was created through automatic machine translation of the original English version. The Swedish corpus was then evaluated on the three criteria meaning preservation, formality preservation and fluency preservation. The results of the study indicated that the Swedish model had the capacity to match the quality of the English model but was held back by the inferior quality of the Swedish corpus. The study also highlighted the need for task specific corpus in Swedish. / Överföring av formalitetsstil syftar på uppgiften att automatiskt omvandla ett stycke text från en nivå av formalitet till en annan. Tidigare forskning har undersökt olika metoder för att utföra uppgiften på engelsk text men vid tiden för detta projekt fanns det enligt författarens vetskap inga tidigare studier som analyserat kvaliteten för överföring av formalitetsstil på svensk text. Syftet med detta arbete var att undersöka hur en modell tränad för överföring av formalitetsstil på svensk text presterar. Detta gjordes genom att jämföra kvaliteten på en modell tränad för överföring av formalitetsstil på svensk text, med en motsvarande modell tränad på engelsk text. Båda modellerna implementerades som kodnings-avkodningsmodeller, vars vikter initierats med hjälp av två befintliga Bidirectional Encoder Representations from Transformers (BERT)-modeller, förtränade på svensk respektive engelsk text. De två modellerna finjusterades för omvandling både från informell stil till formell och från formell stil till informell. Under finjusteringen användes en svensk och en engelsk version av korpusen Grammarly’s Yahoo Answers Formality Corpus (GYAFC). Den svenska versionen av GYAFC skapades genom automatisk maskinöversättning av den ursprungliga engelska versionen. Den svenska korpusen utvärderades sedan med hjälp av de tre kriterierna betydelse-bevarande, formalitets-bevarande och flödes-bevarande. Resultaten från studien indikerade att den svenska modellen hade kapaciteten att matcha kvaliteten på den engelska modellen men hölls tillbaka av den svenska korpusens sämre kvalitet. Studien underströk också behovet av uppgiftsspecifika korpusar på svenska.