Human-computer dialogue design considerations

The three critical elements of quality human-computer dialogue design include a compilation of existing design guidelines, behavioral research to expand the general dialogue principles, and a computer-aided implementation for retrieval of the guidelines by dialogue authors. The need for empirically based dialogue guidelines relating to generic human-computer taks is stressed. The results of two studies dealing with interactive text editing are presented as examples of research directed toward specifying dialogue design principles and developing formal tools for human-computer dialogue research. One of these studies deals with a methodology for developing user models, and the second study deals with the design of HELP information. Computer-aiding in the form of rule-based systems for selecting appropriate dialogue guidelines and software tools for authoring dialogues are discussed as means for implementing these dialogue design considerations.     

文本情感对话系统研究综述

对话系统作为人机交互的重要方式,有着广泛的应用前景.现有的对话系统专注于解决语义一致性和内容丰富性等问题,对于提高人机交互以及产生人机共鸣方向的研究关注度不高.如何让生成的语句在具有语义相关性的基础上更自然地与用户交流是当前对话系统面临的主要问题之一.首先对对话系统进行了整体情况的概括.接着介绍了情感对话系统中的对话情...     

口语对话系统中对话管理方法研究综述

口语对话系统是人机交互领域的核心技术,也是实现和谐人机交互的重要途径,具有重大的研究意义和应用价值,其中的各项理论和技术的研究进展一直备受关注.较为全面深入地总结了对话管理及口语对话系统的研究进展和现状.首先阐述了口语对话系统中的主要研究问题,包括系统各模块的研究内容与关键技术、系统的可移植性和鲁棒性设计等;然后从理论模型、研究进展及可用性等角度系统地剖析了现有的多种口语对话管理策略;最后展望了未来可能的研究方向和亟待解决的问题.     

面向虚实融合的人机交互

面向虚实融合的人机交互涉及计算机科学、认知心理学、人机工程学、多媒体技术和虚拟现实等领域，旨在提高人机交互的效率，同时响应人类认知与情感的需求，在办公教育、机器人和虚拟/增强现实设备中都有广泛应用。本文从人机交互涉及感知计算、人与机器人交互及协同、个性化人机对话和数据可视化等4个维度系统阐述面向虚实融合人机交互的发展现状。对国内外研究现状进行对比，展望未来的发展趋势。本文认为兼具可迁移与个性化的感知计算、具备用户行为深度理解的人机协同、用户自适应的对话系统等是本领域的重要研究方向。     

Adaptive dialogue management using intent clustering and fuzzy rules

Conversational systems have become an element of everyday life for billions of users who use speech‐based interfaces to services, engage with personal digital assistants on smartphones, social media chatbots, or smart speakers. One of the most complex tasks in the development of these systems is to design the dialogue model, the logic that provided a user input selects the next answer. The dialogue model must also consider mechanisms to adapt the response of the system and the interaction style according to different groups and user profiles. Rule‐based systems are difficult to adapt to phenomena that were not taken into consideration at design‐time. However, many of the systems that are commercially available are based on rules, and so are the most widespread tools for the development of chatbots and speech interfaces. In this article, we present a proposal to: (a) automatically generate the dialogue rules from a dialogue corpus through the use of evolving algorithms, (b) adapt the rules according to the detected user intention. We have evaluated our proposal with several conversational systems of different application domains, from which our approach provided an efficient way for adapting a set of dialogue rules considering user utterance clusters.     

多模态人机交互综述

多模态人机交互旨在利用语音、图像、文本、眼动和触觉等多模态信息进行人与计算机之间的信息交换。在生理心理评估、办公教育、军事仿真和医疗康复等领域具有十分广阔的应用前景。本文系统地综述了多模态人机交互的发展现状和新兴方向,深入梳理了大数据可视化交互、基于声场感知的交互、混合现实实物交互、可穿戴交互和人机对话交互的研究进展以及国内外研究进展比较。本文认为拓展新的交互方式、设计高效的各模态交互组合、构建小型化交互设备、跨设备分布式交互、提升开放环境下交互算法的鲁棒性等是多模态人机交互的未来研究趋势。     

Icon-based human-computer interaction

This paper is concerned with the use of icons in human-computer interaction (HCI). Icons are pictographic representations of data or processes within a computer system, which have been used to replace commands and menus as the means by which the computer supports a dialogue with the end-user. They have been applied principally to graphics-based interfaces to operating systems, networks and document-processing software.The paper attempts to provide a more systematic treatment of icon interfaces than has hitherto been made, and to create a classification which it is hoped will be of use to the dialogue designer. The characteristics, advantages and disadvantages of icon-based dialogues are described. Metaphors, design alternatives, display structures and implementation factors are discussed, and there is a summary of some icon design guidelines drawn from a variety of sources. Some mention is also made of attempts by researchers to measure the effectiveness of icon designs empirically.     

Integrating methods of human-computer interface design with structured systems development

Various methods for specification and design of the human-computer interface have been proposed but practice of such methods is not widespread. Possible reasons for this may be the lack of integration of human-computer interface design with software engineering and the specialized nature of HCI methods. A method of interface design is proposed which integrates the development of the human-computer interface with structured systems analysis and design. The method covers task and user analysis, interface specification and dialogue design. A case study of a library system is used to illustrate the method which is discussed in relation to different approaches that have been adopted for interface specification and design. It is argued that software design methods should cover all aspects of process design and the human-computer interface.     

Improving natural language and speech interfaces by the use of metalinguistic phenomena

Current shortcomings of Natural Language and Speech recognition interfaces are discussed. The argument examined is that people's familiarity with Natural Language and Speech, generally regarded as the raison d'etre of such interfaces, is in fact a barrier to their effective use. It is demonstrated, however, that prudent use of human metalingusitic strategies can alleviate some of the shortcomings in such interfaces. Examples are provided of metalinguistic strategies (response matching, mutual modelling and message adaptation), identified in human-human dialogue, being investigated in the laboratory and adapted for effective use in the design of human-computer dialogues.     

Developing and evaluating an interactive system for producing human-computer interfaces

The Author's Interactive Dialogue Environment (AIDE) of the Dialogue Management System is an integrated set of interactive tools for developing human-computer interfaces. AIDE is used by an interface specialist, called a dialogue developer, to implement an interface by directly manipulating and defining its objects, rather than by the traditional method of writing source code. This paper describes the structural dialogue transaction model upon which AIDE is based, describes the use of AIDE for developing human-computer interfaces, and describes an empirical study comparing use of AIDE with use of a programming language for implementing a human-computer interface. Results of this study empirically support, possibly for the first time, the claim that interactive tools for interface development, such as AIDE, can improve productivity and reduce frustration in developing interfaces over traditional programming techniques for interface development.     

Shaping user input: a strategy for natural language dialogue design

Traditional approaches to natural language dialogue interface design have adopted ordinary human-human conversation as the model for online human-computer interaction. The attempt to deal with all the subtleties of natural dialogues, such as topic focus, coherence, ellipsis, pronominal reference, etc. has resulted in prototype systems that are enormously complex and computationally expensive.

In a series of experiments^†, we explored ways of minimizing the processing burden of a dialogue system by channeling user input towards a more tractable, though still natural, form of Englishlanguage questions. Through linking a pair of terminals, we presented subjects with two different dialogue styles as a framework for online help in the domain of word-processing. The first dialogue style involved ordinary conversational format. The second style involved a simulation of an automated dialogue system, including apparent processing restrictions and ‘system process messages’ to inform the subject of the steps taken by the system during query analysis. In both cases human tutors played the role of the help system. After each dialogue session, subjects were interviewed to determine their assessments of the naturalness and usability of the dialogue interface.

We found that user input became more tractable to parsing and query analysis as the dialogue style became more formalized, yet the subjective assessment of naturalness and usability remained fairly constant. This suggests that techniques for channeling user input in a dialogue system may be effectively employed to reduce processing demands without compromising the benefits of a natural language interface. Theoretically, this data lends support to the hypothesis that unrestricted human-human conversation is not the most appropriate model for the design of human-computer dialogue interfaces.     

面向任务型的对话系统研究进展

基于人工智能技术的人机对话系统在人机交互、智能助手、智能客服、问答咨询等多个领域应用日益广泛,这极大地促进了自然语言理解及生成、对话状态追踪和端到端的深度学习模型构建等相关理论与技术的发展,并成为目前工业界与学术界共同关注的研究热点之一。该文聚焦特定场景下的任务型对话系统,在对其基本概念进行形式化定义的基础上,围绕着以最少的对话轮次来获得最佳用户需求相匹配的对话内容为目标,针对目前存在的复杂业务场景下基于自然语言的用户意图的准确理解和识别、针对训练数据的标注依赖及模型结果的可解释性不足,以及多模态条件下对话内容的个性化生成这三个重大的技术问题和挑战,对当前的技术与研究进展进行系统地对比分析和综述,为进一步的研究工作奠定基础。同时,对新一代的面向任务型的人机对话系统未来的关键研究方向与任务进行总结。     

对话情绪识别综述

对话情绪识别是情感计算领域的一个热门研究课题,旨在检测对话过程中每个话语的情感类别。其在对话理解和对话生成方面具有重要的研究意义,同时在社交媒体分析、推荐系统、医疗和人机交互等诸多领域具有广泛的实际应用价值。随着深度学习技术的不断创新和发展,对话情绪识别受到学术界和工业界越来越多的关注,现阶段需要综述性的文章对已有研究成果进行总结,以便更好地开展后续工作。从问题定义、问题切入方式、研究方法、主流数据集等多个角度对该领域的研究成果进行全面梳理,回顾和分析了对话情绪识别任务的发展。对话文本中含有丰富的语义信息,结合视频和音频可以进一步提升建模效果,因此,重点对文本对话情绪识别以及多模态对话情绪识别的方法进行了梳理,立足于当前研究现状,总结了现有对话情绪识别领域存在的开放问题以及未来的发展趋势。     

Sisl: Several Interfaces, Single Logic

Modern interactive services such as information and e-commerce services are becoming increasingly more flexible in the types of user interfaces they support. These interfaces incorporate automatic speech recognition and natural language understanding and include graphical user interfaces on the desktop and web-based interfaces using applets and HTML forms. To what extent can the user interface software be decoupled from the service logic software (the code that defines the essential function of a service)? Decoupling of user interface from service logic directly impacts the flexibility of services, or how easy they are to modify and extend. To explore these issues, we have developed Sisl, an architecture and domain-specific language for designing and implementing interactive services with multiple user interfaces. A key principle underlying Sisl is that all user interfaces to a service share the same service logic. Sisl provides a clean separation between the service logic and the software for a variety of interfaces, including Java applets, HTML pages, speech-based natural language dialogue, and telephone-based voice access. Sisl uses an event-based model of services that allows service providers to support interchangeable user interfaces (or add new ones) to a single consistent source of service logic and data. As part of a collaboration between research and development, Sisl is being used to prototype a new generation of call processing services for a Lucent Technologies switching product.     

招生咨询系统中的信息合成及其应用研究

文章以高校招生信息电话咨询作为实际应用对象,对人机对话系统中的不确定性推理进行了理论分析。并提出了基于证据理论的合成方法。在应用研究中给出了人机对话实验系统的基本算法。并对系统及数据库结构进行了探讨。     

面向任务的基于深度学习的多轮对话系统与技术

自然语言是人类智慧的结晶,以自然语言的形式与计算机进行交互是人们长久以来的期待。随着自然语言处理技术的发展与深度学习方法的兴起,人机对话系统成为了新的研究热点。人机对话系统按照功能可以分为任务导向型对话系统、闲聊型对话系统、问答型对话系统。任务导向型对话系统是一种典型的人机对话系统,旨在帮助用户完成某些特定的任务,有着十分重要的学术意义和应用价值。文中系统地阐述了一种在实际工程应用中的任务导向型对话系统的通用框架,主要包括自然语言理解、对话管理以及自然语言生成3个部分;介绍了上述各部分所采用的经典深度学习和机器学习方法。最后,对自然语言理解任务进行了实证性的实验验证与分析,结果表明文中内容可以为任务导向型对话系统的构建提供有效指导。     

Wizard of Oz support throughout an iterative design process

The Wizard of Oz prototyping approach, widely used in human-computer interaction research, is particularly useful in exploring user interfaces for pervasive, ubiquitous, or mixed-reality systems that combine complex sensing and intelligent control logic. The vast design space for such nontraditional interfaces provides many possibilities for user interaction through one or more modalities and often requires challenging hardware and software implementations. The WOz method helps designers avoid getting locked into a particular design or working under an incorrect set of assumptions about user preferences, because it lets them explore and evaluate designs before investing the considerable development time needed to build a complete prototype.