Stripped of the intent of its author, L. Frank Baum, the children's fairy tale The Wonderful Wizard of Oz was left to be understood only within a changing cultural construct. Historian Hayden White, arguing that the similarities between a novel and a work of history were more significant than their differences, insisted that history was preeminently a subsection of literature. According to White, historical narratives were manifestly verbal fictions, and the only acceptable grounds upon which the historian should choose his historical perspective were the moral and the aesthetic. White conflated historical consciousness with myth and blurred the boundary that had long divided history from fiction. Just as changing cultural concerns infused the Dorothy of Baum's children's literature with meaning so social, cultural, and moral imperatives came to dictate the content of historical stories particularly in the historiography of the Reconstruction era. The twenty first century conception of Reconstruction is different from the conception influential at the start of the twentieth. In assessing the scholarship of William A. Dunning, contemporary historians have adopted a new paradigm when describing the scholar's Reconstruction accounts. Modern commentators reject Dunning's authorial intention and the contextual framework needed to define it. Thus, Dunning has receded into the "realm of myth." Careful attendance to Dunning's historical context, contemporary audience, and his authorial intent, will reposition the perspective for analysis of Dunning's work. Removing Dunning from abstract analysis will allow historians to arrive at an understanding of his work, and view the importance of the real Dunning, rather than the fabricated image constructed from a partial and even fragmented reading of his work. / Taking Dunning on his own terms restores a meaningful past and brings into bas-relief the tremendous advances the U. S. of twenty first century has made in reshaping social and political patterns.Taking theReconstruction era on its own terms impels historians to move beyond Dunning and return in their research to revisit primary records and documents as they work to clear the grisly ground of Reconstruction historiography for further fruitful examination. / by Kathleen P. Barsalou. / Thesis (Ph.D.)--Florida Atlantic University, 2008. / Includes bibliography. / Electronic reproduction. Boca Raton, FL : 2008 Mode of access: World Wide Web.

This thesis presents work done during the last ten years on developing five multimodal spoken dialogue systems, and the empirical user studies that have been conducted with them. The dialogue systems have been multimodal, giving information both verbally with animated talking characters and graphically on maps and in text tables. To be able to study a wider rage of user behaviour each new system has been in a new domain and with a new set of interactional abilities. The five system presented in this thesis are: The Waxholm system where users could ask about the boat traffic in the Stockholm archipelago; the Gulan system where people could retrieve information from the Yellow pages of Stockholm; the August system which was a publicly available system where people could get information about the author Strindberg, KTH and Stockholm; the AdAptsystem that allowed users to browse apartments for sale in Stockholm and the Pixie system where users could help ananimated agent to fix things in a visionary apartment publicly available at the Telecom museum in Stockholm. Some of the dialogue systems have been used in controlled experiments in laboratory environments, while others have been placed inpublic environments where members of the general public have interacted with them. All spoken human-computer interactions have been transcribed and analyzed to increase our understanding of how people interact verbally with computers, and to obtain knowledge on how spoken dialogue systems canutilize the regularities found in these interactions. This thesis summarizes the experiences from building these five dialogue systems and presents some of the findings from the analyses of the collected dialogue corpora. / QC 20100611

情報処理学会研究報告音声言語情報処理;2002-SLP-44-23

情報処理学会研究報告. SLP, 音声言語情報処理; 2003-SLP-49-46 第5回音声言語シンポジウム

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.

This study aimed to explore the implementation of fairness in intelligent agents to enhance their interactions in our social space. Two distinct investigations, an experiment, and a focus group, were conducted to examine the impact of unfair treatment by non-anthropomorphic and anthropomorphic agents, where we sought to answer the research question: How does experiencing unfair treatment from agents with different appearances influence individuals' perceptions, satisfaction, and trust? The experiment encompassed four experimental conditions combining fair and unfair behaviours with agents displaying human-like or non-human-like appearances. User enactment, Experience prototyping, and the Wizard of Oz technique were employed during the experiment. The focus group aimed to delve into the concept of fairness and its relevance to agents in greater detail. In summary, the study's findings indicate that fairness is a significantly important consideration in agent design. However, the complexity of designing a fair agent proves challenging, due to the subjective and contextual nature where it entangles with various factors. / Toward socially competent AI: Designing multi-user interaction with embodied intelligent agents to support politeness and fairness (SCAI)

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.