No description available.

No description available.

Este trabalho apresenta um estudo sobre como a tecnologia adaptativa pode ser utilizada para aprimorar métodos existentes de gerenciamento de diálogo. O gerenciamento de diálogo é a atividade central em um sistema computacional de diálogo falado, sendo a responsável por decidir as ações comunicativas que devem ser enviadas ao usuário. Para evidenciar pontos que pudessem ser melhorados através do uso da tecnologia adaptativa, faz-se uma revisão literária ampla do gerenciamento do diálogo. Esta revisão também permite elencar critérios existentes e criar outros novos para avaliar gerenciadores de diálogos. Um modelo de gerenciamento adaptativo baseado em máquinas de estados, denominado Adaptalker, é então proposto e utilizado para criar um framework de desenvolvimento de gerenciadores de diálogo, o qual foi exercitado pelo desenvolvimento ilustrativo de uma aplicação simples de venda de pizzas. A análise desse exemplo permite observar como a adaptatividade é utilizada para aperfeiçoar o modelo, tornando-o capaz, por exemplo, de lidar de forma mais eficiente tanto com o reparo do diálogo quanto com a iniciativa do usuário. As regras de gerenciamento do Adaptalker são organizadas em submáquinas, que trabalham de forma concorrente para decidir qual a próxima ação comunicativa. / This work presents a study on how to apply adaptive technologies to improve existing dialog management methodologies. Dialog management is the central activity of a spoken dialog system, being responsible for choosing the communicative actions sent to the system user. In order to evidence parts that can be improved with adaptive technology, a large review on dialog management is presented. This review allows us to point existing criteria and create new ones to evaluate dialog managers. An adaptive management model based on finite state-based spoken dialog systems, Adaptalker, is proposed and used to build a development framework of dialog managers, which is illustrated by creating a pizza selling application. Analysis of this example allows us to observe how to use adaptivity to improve the model, allowing it to handle both dialog repair and user initiative more efficiently. Adaptalker groups its management rules in submachines that work concurrently to choose the next communication action.

Este trabalho apresenta um estudo sobre como a tecnologia adaptativa pode ser utilizada para aprimorar métodos existentes de gerenciamento de diálogo. O gerenciamento de diálogo é a atividade central em um sistema computacional de diálogo falado, sendo a responsável por decidir as ações comunicativas que devem ser enviadas ao usuário. Para evidenciar pontos que pudessem ser melhorados através do uso da tecnologia adaptativa, faz-se uma revisão literária ampla do gerenciamento do diálogo. Esta revisão também permite elencar critérios existentes e criar outros novos para avaliar gerenciadores de diálogos. Um modelo de gerenciamento adaptativo baseado em máquinas de estados, denominado Adaptalker, é então proposto e utilizado para criar um framework de desenvolvimento de gerenciadores de diálogo, o qual foi exercitado pelo desenvolvimento ilustrativo de uma aplicação simples de venda de pizzas. A análise desse exemplo permite observar como a adaptatividade é utilizada para aperfeiçoar o modelo, tornando-o capaz, por exemplo, de lidar de forma mais eficiente tanto com o reparo do diálogo quanto com a iniciativa do usuário. As regras de gerenciamento do Adaptalker são organizadas em submáquinas, que trabalham de forma concorrente para decidir qual a próxima ação comunicativa. / This work presents a study on how to apply adaptive technologies to improve existing dialog management methodologies. Dialog management is the central activity of a spoken dialog system, being responsible for choosing the communicative actions sent to the system user. In order to evidence parts that can be improved with adaptive technology, a large review on dialog management is presented. This review allows us to point existing criteria and create new ones to evaluate dialog managers. An adaptive management model based on finite state-based spoken dialog systems, Adaptalker, is proposed and used to build a development framework of dialog managers, which is illustrated by creating a pizza selling application. Analysis of this example allows us to observe how to use adaptivity to improve the model, allowing it to handle both dialog repair and user initiative more efficiently. Adaptalker groups its management rules in submachines that work concurrently to choose the next communication action.

Human behavior varies widely as does the design of spoken dialog systems (SDS). The search for predictors to match a user’s preference and efficiency for a specific dialog interface type in an SDS was the focus of this research. By using personality as described by the Five-Factor Method (FFM) and the Wizard of Oz technique for delivering three system initiatives of the SDS, participants interacted with each of the SDS initiatives in scheduling an airline flight. The three system initiatives were constructed as strict system, which did not allow the user control of the interaction; mixed system, which allowed the user some control of the interaction but with a system override; and user system, which allowed the user control of the interaction. In order to eliminate gender bias in using the FFM as the instrument, participants were matched in gender and age. Participants were 18 years old to 70 years old, passed a hearing test, had no disability that prohibited the use of the SDS, and were native English speakers. Participants completed an adult consent form, a 50-question personality assessment as described by the FFM, and the interaction with the SDS. Participants also completed a system preference indication form at the end of the interaction. Observations for efficiency were recorded on paper by the researcher. Although the findings did not show a definitive predictor for a SDS due to the small population sample, by using a multinomial regression approach to the statistical analysis, odds ratios of the data helped draw conclusions that support certain personality factors as important roles in a user’s preference and efficiency in choosing and using a SDS. This gives an area for future research. Also, the presumption that preference and efficiency always match was not supported by the results from two of the three systems. An additional area for future research was discovered in the gender data. Although not an initial part of the research, the data shows promise in predicting preference and efficiency for certain SDS. Future research is indicated.

Using references in language is a major part of communication, and understanding them is not a challenge for humans. Recent years have seen increased usage of dialog systems that interact with humans in natural language to assist them in various tasks, but even the most sophisticated systems still struggle with understanding references. In this thesis, we adapt a coreference resolution system for usage in dialog systems and try to understand what is needed for an efficient understanding of references in dialog systems. We annotate a portion of logs from a customer service system and perform an analysis of the most common coreferring expressions appearing in this type of data. This analysis shows that most coreferring expressions are nominal and pronominal, and they usually appear within two sentences of each other. We implement Stanford's Multi-Pass Sieve with some adaptations and dialog-specific changes and integrate it into a dialog system framework. The preprocessing pipeline makes use of already existing NLP-tools, while some new ones are added, such as a chunker, a head-finding algorithm and a NER-like system. To analyze both user input and output of the system, we deploy two separate coreference resolution systems that interact with each other. An evaluation is performed on the system and its separate parts in five most common evaluation metrics. The system does not achieve state-of-the art numbers, but because of its domain-specific nature that is expected. Some parts of the system do not have any effect on the performance, while the dialog-specific changes contribute to it greatly. An error analysis is concluded and reveals some problems with the implementation, but more importantly, it shows how the system could be further improved by using other types of knowledge and dialog-specific features.

Research endeavors on spoken dialogue systems in the 1990s and 2000s have led to the deployment of commercial spoken dialogue systems (SDS) in microdomains such as customer service automation, reservation/booking and question answering systems. Recent research in SDS has been focused on the development of applications in different domains (e.g. virtual counseling, personal coaches, social companions) which requires more sophistication than the previous generation of commercial SDS. The focus of this research project is the delivery of behavior change interventions based on the brief intervention counseling style via spoken dialogue systems. Brief interventions (BI) are evidence-based, short, well structured, one-on-one counseling sessions. Many challenges are involved in delivering BIs to people in need, such as finding the time to administer them in busy doctors' offices, obtaining the extra training that helps staff become comfortable providing these interventions, and managing the cost of delivering the interventions. Fortunately, recent developments in spoken dialogue systems make the development of systems that can deliver brief interventions possible. The overall objective of this research is to develop a data-driven, adaptable dialogue system for brief interventions for problematic drinking behavior, based on reinforcement learning methods. The implications of this research project includes, but are not limited to, assessing the feasibility of delivering structured brief health interventions with a data-driven spoken dialogue system. Furthermore, while the experimental system focuses on harmful alcohol drinking as a target behavior in this project, the produced knowledge and experience may also lead to implementation of similarly structured health interventions and assessments other than the alcohol domain (e.g. obesity, drug use, lack of exercise), using statistical machine learning approaches. In addition to designing a dialog system, the semantic and emotional meanings of user utterances have high impact on interaction. To perform domain specific reasoning and recognize concepts in user utterances, a named-entity recognizer and an ontology are designed and evaluated. To understand affective information conveyed through text, lexicons and sentiment analysis module are developed and tested.

El objetivo principal de la tesis que se presenta es el estudio y desarrollo de diferentes metodologías para la gestión del diálogo en sistemas de diálogo hablado. El principal reto planteado en la tesis reside en el desarrollo de metodologías puramente estadísticas para la gestión del diálogo, basadas en el aprendizaje de un modelo a partir de un corpus de diálogos etiquetados. En este campo, se presentan diferentes aproximaciones para realizar la gestión, la mejora del modelo estadístico y la evaluación del sistema del diálogo. Para la implementación práctica de estas metodologías, en el ámbito de una tarea específica, ha sido necesaria la adquisición y etiquetado de un corpus de diálogos. El hecho de disponer de un gran corpus de diálogos ha facilitado el aprendizaje y evaluación del modelo de gestión desarrollado. Así mismo, se ha implementado un sistema de diálogo completo, que permite evaluar el funcionamiento práctico de las metodologías de gestión en condiciones reales de uso. Para evaluar las técnicas de gestión del diálogo se proponen diferentes aproximaciones: la evaluación mediante usuarios reales; la evaluación con el corpus adquirido, en el cual se han definido unas particiones de entrenamiento y prueba; y la utilización de técnicas de simulación de usuarios. El simulador de usuario desarrollado permite modelizar de forma estadística el proceso completo del diálogo. En la aproximación que se presenta, tanto la obtención de la respuesta del sistema como la generación del turno de usuario se modelizan como un problema de clasificación, para el que se codifica como entrada un conjunto de variables que representan el estado actual del diálogo y como resultado de la clasificación se obtienen las probabilidades de seleccionar cada una de las respuestas (secuencia de actos de diálogo) definidas respectivamente para el usuario y el sistema. / Griol Barres, D. (2007). Desarrollo y evaluación de diferentes metodologías para la gestión automática del diálogo [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/1956 / Palancia

Cette thèse par article se compose de quatre articles qui contribuent au domaine de l’apprentissage profond, en particulier dans la compréhension et l’apprentissage des ap- proches neuronales des systèmes de dialogue. Le premier article fait un pas vers la compréhension si les architectures de dialogue neuronal couramment utilisées capturent efficacement les informations présentes dans l’historique des conversations. Grâce à une série d’expériences de perturbation sur des ensembles de données de dialogue populaires, nous constatons que les architectures de dialogue neuronal couramment utilisées comme les modèles seq2seq récurrents et basés sur des transformateurs sont rarement sensibles à la plupart des perturbations du contexte d’entrée telles que les énoncés manquants ou réorganisés, les mots mélangés, etc. Le deuxième article propose d’améliorer la qualité de génération de réponse dans les systèmes de dialogue de domaine ouvert en modélisant conjointement les énoncés avec les attributs de dialogue de chaque énoncé. Les attributs de dialogue d’un énoncé se réfèrent à des caractéristiques ou des aspects discrets associés à un énoncé comme les actes de dialogue, le sentiment, l’émotion, l’identité du locuteur, la personnalité du locuteur, etc. Le troisième article présente un moyen simple et économique de collecter des ensembles de données à grande échelle pour modéliser des systèmes de dialogue orientés tâche. Cette approche évite l’exigence d’un schéma d’annotation d’arguments complexes. La version initiale de l’ensemble de données comprend 13 215 dialogues basés sur des tâches comprenant six domaines et environ 8 000 entités nommées uniques, presque 8 fois plus que l’ensemble de données MultiWOZ populaire. / This thesis by article consists of four articles which contribute to the field of deep learning, specifically in understanding and learning neural approaches to dialog systems. The first article takes a step towards understanding if commonly used neural dialog architectures effectively capture the information present in the conversation history. Through a series of perturbation experiments on popular dialog datasets, wefindthatcommonly used neural dialog architectures like recurrent and transformer-based seq2seq models are rarely sensitive to most input context perturbations such as missing or reordering utterances, shuffling words, etc. The second article introduces a simple and cost-effective way to collect large scale datasets for modeling task-oriented dialog systems. This approach avoids the requirement of a com-plex argument annotation schema. The initial release of the dataset includes 13,215 task-based dialogs comprising six domains and around 8k unique named entities, almost 8 times more than the popular MultiWOZ dataset. The third article proposes to improve response generation quality in open domain dialog systems by jointly modeling the utterances with the dialog attributes of each utterance. Dialog attributes of an utterance refer to discrete features or aspects associated with an utterance like dialog-acts, sentiment, emotion, speaker identity, speaker personality, etc. The final article introduces an embedding-free method to compute word representations on-the-fly. This approach significantly reduces the memory footprint which facilitates de-ployment in on-device (memory constraints) devices. Apart from being independent of the vocabulary size, we find this approach to be inherently resilient to common misspellings.