No description available.

Computer programs designed to converse with humans in natural language provide a framework against which to test supra-sentential theories of language production and interpretation. This thesis seeks to flesh out, in terms of a computer model, two basic assumptions concerning prosody-that speakers use intonation to convey intention, or attitude, and that prosodic prominence serves to convey conceptual prommence. A model of an information-providing agent in is proposed, based on an analysis of a corpus of spontaneous dialogues. This uses an architecture of communicating processes, which perform interpretation, application-specific planning, repair, and the production of output. Dialogue acts are then defined as feature bundles corresponding to significant events. A corpus of read dialogues is analysed in terms of these features, and using conventional intonational labelling. Correlations between the two are examined. Prosodic prominence is examined at three levels. At the level of surface encoding, re-use of substrings and structural parallelism can reduce processing for the speaker, and the listener. At the level of conceptual planning, similar benefits exist, given that speakers and listeners assume a common discourse model wherever possible. At these levels use is made of a short-term buffer of recent forms. A speaker may additionally use contrastive prominence to draw the listener's attention to disparities. Finally, at the level of intentions, a speaker wish to highlight certain information, regardless of accessibility. Prosodic focus is represented relationally, rather than via a simple binary-valued feature. This has the advantage of facilitating the mapping between levels; it also renders straightforward the notion of focus as the product of a number of potentially conflicting influences. Those parts of the theory concerned with discourse representation, language generation, and prosodic focus have been implemented as part of the Sundial dialogue system. In this system, discoursal and pragmatic decisions affecting prosody are converted to annotations on a text string, for realisation by a rule-based synthesizer.

No description available.

Much of the data found on the world wide web is in numeric, tabular, or other nontextual format (e.g., weather forecast tables, stock market charts, live sensor feeds), and thus inaccessible to non-experts or laypersons. However, most conventional search engines and natural language processing tools (e.g., summarisers) can only handle textual input. As a result, data in non-textual form remains largely inaccessible. Concept-to-text generation refers to the task of automatically producing textual output from non-linguistic input, and holds promise for rendering non-linguistic data widely accessible. Several successful generation systems have been produced in the past twenty years. They mostly rely on human-crafted rules or expert-driven grammars, implement a pipeline architecture, and usually operate in a single domain. In this thesis, we present several novel statistical models that take as input a set of database records and generate a description of them in natural language text. Our unique idea is to combine the processes of structuring a document (document planning), deciding what to say (content selection) and choosing the specific words and syntactic constructs specifying how to say it (lexicalisation and surface realisation), in a uniform joint manner. Rather than breaking up the generation process into a sequence of local decisions, we define a probabilistic context-free grammar that globally describes the inherent structure of the input (a corpus of database records and text describing some of them). This joint representation allows individual processes (i.e., document planning, content selection, and surface realisation) to communicate and influence each other naturally. We recast generation as the task of finding the best derivation tree for a set of input database records and our grammar, and describe several algorithms for decoding in this framework that allows to intersect the grammar with additional information capturing fluency and syntactic well-formedness constraints. We implement our generators using the hypergraph framework. Contrary to traditional systems, we learn all the necessary document, structural and linguistic knowledge from unannotated data. Additionally, we explore a discriminative reranking approach on the hypergraph representation of our model, by including more refined content selection features. Central to our approach is the idea of porting our models to various domains; we experimented on four widely different domains, namely sportscasting, weather forecast generation, booking flights, and troubleshooting guides. The performance of our systems is competitive and often superior compared to state-of-the-art systems that use domain specific constraints, explicit feature engineering or labelled data.

Automatic story generation has a long-standing tradition in the field of Artificial Intelligence. The ability to create stories on demand holds great potential for entertainment and education. For example, modern computer games are becoming more immersive, containing multiple story lines and hundreds of characters. This has substantially increased the amount of work required to produce each game. However, by allowing the game to write its own story line, it can remain engaging to the player whilst shifting the burden of writing away from the game’s developers. In education, intelligent tutoring systems can potentially provide students with instant feedback and suggestions of how to write their own stories. Although several approaches have been introduced in the past (e.g., story grammars, story schema and autonomous agents), they all rely heavily on handwritten resources. Which places severe limitations on its scalability and usage. In this thesis we will motivate a new approach to story generation which takes its inspiration from recent research in Natural Language Generation. Whose result is an interactive data-driven system for the generation of children’s stories. One of the key features of this system is that it is end-to-end, realising the various components of the generation pipeline stochastically. Knowledge relating to the generation and planning of stories is leveraged automatically from corpora and reformulated into new stories to be presented to the user. We will also show that story generation can be viewed as a search task, operating over a large number of stories that can be generated from knowledge inherent in a corpus. Using trainable scoring functions, our system can search the story space using different document level criteria. In this thesis we focus on two of these, namely, coherence and interest. We will also present two major paradigms for generation through search, (a) generate and rank, and (b) genetic algorithms. We show the effects on perceived story interest, fluency and coherence that result from these approaches. In addition, we show how the explicit use of plots induced from the corpus can be used to guide the generation process, providing a heuristically motivated starting point for story search. We motivate extensions to the system and show that additional modules can be used to improve the quality of the generated stories and overall scalability. Finally we highlight the current strengths and limitations of our approach and discuss possible future approaches to this field of research.

No description available.

This thesis explores approaches to modelling individual differences in language use. The differences under consideration fall into two broad categories: Variation of the personality projected through language, and modelling of language alignment behaviour between dialogue partners. In a way, these two aspects oppose each other – language related to varying personalities should be recognisably different, while aligning speakers agree on common language during a dialogue. The central hypothesis is that such variation can be captured and produced with restricted computational means. Results from research on personality psychology and psycholinguistics are transformed into a series of lexically-based Affective Language Production Models (ALPMs) which are parameterisable for personality and alignment. The models are then explored by varying the parameters and observing the language they generate. ALPM-1 and ALPM-2 re-generate dialogues from existing utterances which are ranked and filtered according to manually selected linguistic and psycholinguistic features that were found to be related to personality. ALPM-3 is based on true overgeneration of paraphrases from semantic representations using the OPENCCG framework for Combinatory Categorial Grammar (CCG), in combination with corpus-based ranking and filtering by way of n-gram language models. Personality effects are achieved through language models built from the language of speakers of known personality. In ALPM-4, alignment is captured via a cache language model that remembers the previous utterance and thus influences the choice of the next. This model provides a unified treatment of personality and alignment processes in dialogue. In order to evaluate the ALPMs, dialogues between computer characters were generated and presented to human judges who were asked to assess the characters’ personality. In further internal simulations, cache language models were used to reproduce results of psycholinguistic priming studies. The experiments showed that the models are capable of producing natural language dialogue which exhibits human-like personality and alignment effects.

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

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