限定领域口语对话系统中超出领域话语的对话行为识别

由于领域外话语具有内容短小、表达多样性、开放性及口语化等特点,限定领域口语对话系统中超出领域话语的对话行为识别是一个挑战。该文提出了一种结合外部无标签微博数据的随机森林对话行为识别方法。该文采用的微博数据无需根据应用领域特点专门收集和挑选,又与口语对话同样具有口语化和表达多样性的特点,其训练得到的词向量在超出领域话语出现超出词汇表字词时提供了有效的相似性扩展度量。随机森林模型具有较好的泛化能力,适合训练数据有限的分类任务。中文特定领域的口语对话语料库测试表明,该文提出的超出领域话语的对话行为识别方法取得了优于最大熵、卷积神经网络等短文本分类研究进展中的方法的效果。     

口语对话管理综述*

主要介绍了口语对话系统中对话管理的作用、基本问题和设计方法。对话管理在整个对话系统中处于核心地位,控制整个对话的进行,负责对用户输入的理解以及根据领域内容决定系统对用户的反应。对话管理的设计主要有基于状态图的结构（有限状态机）、填充槽结构和基于任务的结构三种方法,提出了一种基于逻辑表达式的结构,并设计了状态图/逻辑表达式双层结构。     

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.     

限定领域口语对话系统中超出领域话语的协处理方法

领域外话语的开放性、口语化以及表达多样性,使得现有的限定领域口语对话系统不能很好地处理超出领域话语。该文提出了一种限定领域口语对话系统协处理方案,基于人工智能标记语言AIML,设计一套理解开放语义用户话语的理解模板,并对未匹配话语基于话语相似度进行理解模板分类,进而采用扩展有限状态自动机处理模式,结合对话流程上下文的状态及信息,实现理解模板到应答模板的转换,改变了单纯模板匹配方法在对话流程控制方面的相对缺失。中文手机导购领域的测试表明,该文所提出的协处理方法能有效地辅助口语对话系统完成限定领域完整对话流程,得到更好的用户满意度。
     

对话管理中基于槽特征有限状态自动机的方法研究

对话系统的研究已经成为人机交互技术发展的新热点。而对话管理则是其中最重要的组成部分．该文在当前对话管理的各种实现方法的基础上,提出了一种基于槽特征的自动机设计方法,其中应用了状态压缩和状态集、动作集的子空间划分。并着重以确认过程为例,阐述了确认策略控制函数及其对对话过程的影响．文中还提出了一种树形的意图分层结构,并将这种分层结构应用于主题检测与主题切换,成功解决了多主题对话系统的主题切换问题．最后,实验表明该文提出的设计方案在策略控制、主题检测与主题切换等方面具有较好性能,同时也具有一定扩展性．     

Depth-of-Field Blur Effects for First-Person Navigation in Virtual Environments

Depth-of-field blur effects are well-known depth cues in human vision. Computer graphics pipelines added DOF effects early to enhance imagery realism, but real-time VR applications haven't yet introduced visual blur effects. The authors describe new techniques to improve blur rendering and report experimental results from a prototype video game implementation.     

汉语股票实时行情查询对话系统

介绍了一个用于股票实时行情查询的口语化的人机对话系统,该系统集成了语音识别、语言理解、对话控制等技术。文中定义了一个情景语义框架模型,较好地处理了口语理解系统的一些难点。     

JAPE: A Prototyping System for Collaborative Virtual Environments

We present JAPE, a flexible prototyping system to support the design of a new advanced collaborative virtual environment. We describe the utilization of different hard- and software components to quickly build a flexible, yet powerful test bed for application and algorithm development. These components include a 3-D rendering toolkit, live video acquisition, speech transmission, and the control of tracking and interaction devices. To facilitate the simultaneous design of applications and algorithms that take advantage of unique features of new collaborative virtual environments, we provide the developer with a flexible prototyping toolkit which emulates the functionality of the final system. The applicability of JAPE is demonstrated with several prototype applications and algorithms.     

限定领域口语对话系统中的商品属性抽取

按功能或问题域划分,商品属性抽取(product feature mining)在限定领域的对话系统中属于口语语言理解(spoken language understanding, SLU)的范畴。商品属性抽取任务只关注自然文本中描述商品属性的特定部分,它是细粒度观点抽取(fine-grained opinion mining)的一个重要的子任务。现有的商品属性抽取技术主要建立在商品的评论语料上,该文以手机导购对话系统为背景,将商品属性抽取应用到整个对话过程中,增强对话系统应答的针对性。使用基于CBOW (continuous bag of words)语言模型的word2vector(W2V)对词汇的语义层面建模,提出一个针对口语对话的指数型变长静态窗口特征表达框架,捕捉不同距离词语组合的重要特征,使用卷积神经网络(convolutional neural network, CNN)结合词汇的语义和上下文层面对口语对话语料中的商品属性进行抽取。词嵌入模型给出了当前词和所给定的属性类别是否存在相关性的证据,而所提出的特征表达框架则是为了解决一词多义的问题。实验结果表明,该方法取得了优于研究进展中方法的商品属性识别效果。     

陪护机器人口语对话系统设计与实现

针对陪护机器人口语对话系统的难点给出了相应的解决方案：以话题为单位的聊天机器人知识库构建规则、简单有效的句子相似度计算方法、准确高效的答案检索模块。通过对78个回合的实际聊天结果的统计分析,验证了解决方案的有效性;同时分析了方案的局限性。     

Designing and Evaluating an Adaptive Spoken Dialogue System

Spoken dialogue system performance can vary widely for different users, as well for the same user during different dialogues. This paper presents the design and evaluation of an adaptive version of TOOT, a spoken dialogue system for retrieving online train schedules. Based on rules learned from a set of training dialogues, adaptive TOOT constructs a user model representing whether the user is having speech recognition problems as a particular dialogue progresses. Adaptive TOOT then automatically adapts its dialogue strategies based on this dynamically changing user model. An empirical evaluation of the system demonstrates the utility of the approach.     

Interactive Control of Large-Crowd Navigation in Virtual Environments Using Vector Fields

Providing interactive control is a hot topic in crowd-navigation research. Here, the authors propose a simple but effective way for authoring a crowd scene. With their governing tool, users can easily drive the flow of crowds by sketching velocities on anchor points in the scene. This approach is fast enough to allow on-the-fly modification of vector fields.     

A Vision for Supporting Autonomous Navigation in Urban Environments

The autonomous navigation systems (ANS), such as autonomous ground vehicles (AGVs), unmanned aerial vehicles (UAVs), and unmanned submersible vehicles (USVs), and modern vehicles with actuators, sensors, and computer control perform three basic functions: context gathering using sensors, processing, and action. Most researchers have put all three functions into the ANS or the robot itself to overcome occlusions and handle the environment's dynamics. However, this causes the ANS and robotic systems to be bulky and expensive. It also impedes the introduction of vehicles with ANS in urban environments, where they must coexist with existing cars and highways. The approach presented distributes the context-gathering and processing functions using sensor networks and wireless communications technologies to reduce costs and make ANS widespread. The system uses sensors mounted on moving vehicles and stationary objects such as lampposts, traffic lights, toll plazas, and buildings to gather information at different levels     

Knowledge-Combining Methodology for Dialogue Design in Spoken Language Systems

In this paper, we propose a strategy for designing dialogue managers in spoken dialogue systems for a restricted domain. This strategy combines several information sources intuition, observation and simulation, in order to maximize the adaptation within the system capability and the expectation of the user. These sources are combined by an iterative process consisting of five steps, where different dialogue alternatives are proposed and evaluated sequentially. The evaluation process includes different measures depending on the information required. Several measures are proposed and analyzed in each step. We also describe a user-modeling technique and an approach for designing the confirmation sub-dialogues based on recognition confidence measures. The knowledge-combining methodology is described and applied to a railway information system. In a subjective evaluation, users from the university gave the system a 3.9 score on a 5-point scale with an average call duration of 205 seconds. The employers of the railway company were more critical of the system. They gave it a score of 2.1 even though the system resolved more than half of the calls (57.8%) within an average call duration of three minutes (185 seconds).     

A Flexible Architecture for Virtual Humans in Networked Collaborative Virtual Environments

Complex virtual human representation provides more natural interaction and communication among participants in networked virtual environments, hence it is expected to increase the sense of being together within the same virtual world. We present a flexible framework for the integration of virtual humans in networked collaborative virtual environments. A modular architecture allows flexible representation and control of the virtual humans, whether they are controlled by a physical user using all sorts of tracking and other devices, or by an intelligent control program turning them into autonomous actors. The modularity of the system allows for fairly easy extensions and integration with new techniques making it interesting also as a testbed for various domains from “classic” VR to psychological experiments. We present results in terms of functionalities, example applications and measurements of performance and network traffic with an increasing number of participants in the simulation.     

三种不同类型语音对话系统的分析与研究

口语对话系统一直是计算机科学领域人类语言技术的热点,能够应用于不同的领域并且具备广阔的前景。将分析国外不同领域的三种典型会话系统：CommandTalk、ITSPOKE 和NICE。将从使用范围与交互方式、语音识别、对话管理、语音合成等几方面分析和研究这三种来自不同领域的对话系统,并提出观点和见解,为国内的口语对话系统研究和开发提供一定的参考和建议。     

一个基于全景图的虚拟环境漫游系统

虚拟现实的实现有两种方法。传统上,使用三维图形学方法进行建模和绘制,这种方法需要繁琐的建模工作和昂贵的专用绘图硬件,而且用三维模型很难真实表现自然景观。基于图像的绘制是实现虚拟现实系统的一种新方法,它克服了三维图形方法的上述缺点,近年来得到了日益广泛的应用。文章讨论了一个基于图像的虚拟环境漫游系统的实现,分析了此类系统的模型,介绍了系统实现中摄像机定标、图像拼接、实时图像变换等关键技术。     

A simulation modelling tool for Distributed Virtual Environments

Distributed Virtual Environments simulate the behaviour and activities of a great number of users interacting in a virtual world over a wide area network. The size of the virtual worlds and the tremendous number of users that these environments are called to support require additional bandwidth and computational resources. For supporting large-scale Distributed Virtual Environments, extended infrastructure is needed in terms of both hardware and software. However, both researchers and application designers do not always have access to such an extended infrastructure and the assessment and evaluation of developed performance improvement techniques becomes extremely difficult. To address this issue, this paper presents a simulation modelling tool, called STEADiVE for networked servers Distributed Virtual Environments that could be used by designers for evaluating the performance of their approaches under different scenarios and system settings. The validation of the simulation modelling tool has showed that it achieves high accuracy in representing a real DVE system. STEADiVE comes to fill in the gap in the area of simulation tools for these systems.     

虚拟计算环境中的虚拟网络

虚拟计算环境是近年来的学术研究热点,而虚拟网络是构成虚拟计算环境的核心技术。本文介绍了主流的虚拟网络构成原理和虚拟网络实现技术,分析了虚拟计算环境中虚拟网络的特点,总结并提出了虚拟网络的性能开销、QoS、自适应和安全性等开放性问题。     

Multi-Speaker Dialogue for Vehicular Navigation and Assistance

Currently, most Spoken Dialogue Systems (SDS) deal only with the interaction between the system and one speaker. In some situations, interaction may occur among several speakers and the system. New functions and improvements need to be made in order to handle a multi-user situation. Studies of the human-computer interaction system that involve multiple users are in their initial stages, and any papers, lectures or studies on the subject are very limited. For these reasons we are motivated to conduct a further study on Multi-Speaker Dialogue Systems (MSDS). In this paper, the interactions between the multiple speakers and the system are classified into three types: independent, cooperative, and conflicting interactions. An algorithm for the multi-speaker dialogue management is proposed. The algorithm determines the interaction type, integrates conversation goals for multiple speakers and keeps the interaction going smoothly. The experiments were carried out in a practical system which can provide useful vehicular information to drivers and passengers. Experimental results show that the proposed algorithm can handle the interaction that occurs in a multi-speaker dialogue system properly. The task completion rate is 76%, and more than 61% of the testers are satisfied with the proposed MSDS system.