This paper introduces the Ninth Dialog System Technology Challenge (DSTC-9). This edition of the DSTC focuses on applying end-to-end dialog technologies for four distinct tasks in dialog systems, namely, 1. Task-oriented dialog Modeling with unstructured knowledge access, 2. Multi-domain task-oriented dialog, 3. Interactive evaluation of dialog, and 4. Situated interactive multi-modal dialog. This paper describes the task definition, provided datasets, baselines and evaluation set-up for each track. We also summarize the results of the submitted systems to highlight the overall trends of the state-of-the-art technologies for the tasks.

No abstract

We propose an interactive image editing system that has a confirmation dialogue strategy using an entropy-based uncertainty calculation on its generated images with Deep Convolutional Generative Adversarial Networks (DCGAN). DCGAN is an image generative model that learns an image manifold of a given dataset and enables continuous change of an image. Our proposed image editing system combines DCGAN with a natural language interface that accepts image editing requests in natural language. Although such a system is helpful for human users, it often faces uncertain requests to generate acceptable images. A promising approach to solve this problem is introducing a dialogue process that shows multiple candidates and confirms the user's intention. However, confirming every editing request creates redundant dialogues. To achieve more efficient dialogues, we propose an entropy-based dialogue strategy that decides when the system should confirm, and enables effective image editing through a dialogue that reduces redundant confirmations. We conducted image editing dialogue experiments using an avatar face illustration dataset for editing by natural language requests. Through quantitative and qualitative analysis, our results show that our entropy-based confirmation strategy achieved an effective dialogue by generating images desired by users. INDEX TERMS Confirmation, generative adversarial networks, image editing, natural language interface.

Research question: The present study examined how organizational climate plays a mediating role in the relationship between job crafting and organizational agility in a government-dependent NSOs suffering from bureaucratic structures and rigid legislation. We therefore hypothesized that employees undertaking job crafting techniques would be most likely to shape positive climates, thereby building organizational agility.Research Methods: Employing a quantitative approach, structural equal modelling (SEM) was performed for testing the research hypothesis. One hundred nighty one employees working in the Iranian Ministry of Sport and Youth were asked to respond to three standard questionnaires.Results and Findings: SEM analyses offered strong support for the research hypothesis referring to positive mediating role of organizational climates. We, discuss how a workplace containing more than two people builds informal organization among employees, as they refine their position to increase social job resources. Implications:The study demonstrated that job crafting has the potential to be linked with positive organizational outcomes and, thereby suggested a practical strategy to select the people for entering NSOs. Presenting a potential workplace pattern for employees to refine their positions in terms of sharing knowledge and carrying out job tasks, the study illustrated a context to empower the human resources.