An Evidential Model for Tracking Initiative in Collaborative Dialogue Interactions

In this paper, we argue for the need to distinguish between task initiative and dialogue initiative, and present an evidential model for tracking shifts in both types of initiatives in collaborative dialogue interactions. Our model predicts the task and dialogue initiative holders for the next dialogue turn based on the current initiative holders and the effect that observed cues have on changing them. Our evaluation across various corpora shows that the use of cues consistently provides significant improvement in the system's prediction of task and dialogue initiative holders. Finally, we show how this initiative tracking model may be employed by a dialogue system to enable the system to tailor its responses to user utterances based on application domain, system's role in the domain, dialogue history, and user characteristics.     

基于DQN的开放域多轮对话策略学习

有效地进行多轮对话是开放域人机对话系统的主要目标之一。目前的神经网络对话生成模型在开放域多轮对话过程中存在着容易产生万能回复、很快陷入死循环的问题;而已有的多轮对话研究工作存在着没有考虑未来对话走向的问题。借鉴强化学习方法考虑全局的视角,该文利用深度强化学习算法DQN(deep Q-network),提出了使用深度价值网络对每一轮的候选句子进行评估,并选择未来收益最大的而非生成概率最大的句子作为回复的多轮对话策略学习方法。实验结果表明,该文提出的方法将多轮对话的平均对话轮数提高了两轮,同时在主观对比评价指标上获胜比例高出了45%。     

Exploring Mixed-Initiative Dialogue Using Computer Dialogue Simulation

This paper experimentally shows that mixed-initiative dialogue is not always more efficient than non-mixed initiative dialogue in route finding tasks. Based on the dialogue model proposed in Conversation Analysis and Discourse Analysis a lá the Birmingham school and Whittaker and Stenton's definition of initiative, we implement dialogue systems and obtain experimental results by making the systems interact with each other. Across a variety of instantiations of the dialogue model, the results show that with easy problems, the efficiency of mixed-initiative dialogue is a little better than or equal to that of non-mixed-initiative dialogue, while with difficult problems mixed-initiative dialogue is less efficient than non-mixed- initiative dialogue.     

User-Tailored Planning of Mixed Initiative Information-Seeking Dialogues

Intelligent dialogue systems usually concentrate on user support at the level of the domain of discourse, following a plan-based approach. Whereas this is appropriate for collaborative planning tasks, the situation in interactive information retrieval systems is quite different: there is no inherent plan-goal hierarchy, and users are known to often opportunistically change their goals and strategies during and through interaction. We need to allow for mixed-initiative retrieval dialogues, where the system evaluates the user's individual dialogue behavior and performs situation-dependent interpretation of user goals, to determine when to take the initiative and to change the control of the dialogue, e.g., to propose (new) problem-solving strategies to the user. In this article, we present the dialogue planning component of a concept- oriented, logic-based retrieval system (MIRACLE). Users are guided through the global stages of the retrieval interaction but may depart, at any time, from this guidance and change the direction of the dialogue. When users submit ambiguous queries or enter unexpected dialogue control acts, abductive reasoning is used to generate interpretations of these user inputs in light of the dialogue history and other internal knowledge sources. Based on these interpretations, the system initiates a short dialogue offering the user suitable options and strategies for proceeding with the retrieval dialogue. Depending on the user's choice and constraints resulting from the history, the system adapts its strategy accordingly.     

Emotion recognition and adaptation in spoken dialogue systems

The involvement of emotional states in intelligent spoken human-computer interfaces has evolved to a recent field of research. In this article we describe the enhancements and optimizations of a speech-based emotion recognizer jointly operating with automatic speech recognition. We argue that the knowledge about the textual content of an utterance can improve the recognition of the emotional content. Having outlined the experimental setup we present results and demonstrate the capability of a post-processing algorithm combining multiple speech-emotion recognizers. For the dialogue management we propose a stochastic approach comprising a dialogue model and an emotional model interfering with each other in a combined dialogue-emotion model. These models are trained from dialogue corpora and being assigned different weighting factors they determine the course of the dialogue.     

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．     

A Computational Mechanism for Initiative in Answer Generation

Initiative in dialogue can be regarded as the speaker taking the opportunity to contribute more information than was his obligation in a particular discourse turn. This paper describes the use of stimulus conditions as a computational mechanism for taking the initiative to provide unrequested information in responses to Yes–No questions, as part of a system for generating answers to Yes–No questions. Stimulus conditions represent types of discourse contexts in which a speaker is motivated to add unrequested information to his answer. Stimulus conditions may be triggered not only by the discourse context at the time when the question was asked, but also by the anticipated context resulting from providing part of the response. We define a set of stimulus conditions based upon previous linguistic studies and a corpus analysis, and describe how evaluation of these stimulus conditions makes use of information from a User Model. Also, we show how the stimulus conditions are used by the generation component of the system. An evaluation was conducted of the implemented system. The results indicate that the responses generated by our system containing extra information provided on the basis of this initiative mechanism are viewed more favorably by users than responses without the extra information.     

主动联想型对话机器人的设计与实现

人机对话系统通常仅是用户命令的执行者,很少能主动发起对话,或依据对话以外的内容展开个性化的人机交互.本文提出了联想型对话机器人的概念和对应设计方案,即通过融合用户提问和用户个人特征的方式产生对话内容,这样的对话系统不仅可以主动发出对话邀请,也可以个性化地回答用户问题,提升人机对话的满意度.文章首先介绍了联想型对话机器人...     

口语对话中的语句主题分析

本文研究如何根据浅层的语义分析确定自然口语对话中的语句主题。首先将对话中的语句主题定义为说话者所关注的显著语义实体,并讨论了这样的语句主题所具有的两个特点(即话语性和连续性) 以及语句主题跟(扩展) 句子类型的关系(因而也介绍了句子类型及其扩展和扩展句子类型的识别) 。然后根据这些建立了语句主题分析算法,并在实际的对话语料中进行分析。实验结果表明,语句主题的分析正确率可达到6111～8716 % ,取决于不同的扩展句子类型和不同的正确率定义。     

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.     

口语对话中非名词指代的消解

代词指代消解是全面理解口语对话不可缺少的一部分。根据口语不同于书面语的特点以及非名词指代先行项的特点,在前人工作的基础上提出了一套适合于在口语对话生语料上消解非名词指代的算法。算法基于非名词指代的右边界规则理论,给出了判断候选先行项属于"线性紧邻"还是"层次紧邻"的判别方法,同时给出了候选先行项的过滤规则。算法在公开发布的口语对话语料Tran is-93上进行了测试,实验结果表明,算法提高了消解的正确率和召回率,能消解更多不同的代词,且适用于口语对话生语料。     

Cooperative Understanding of Utterances and Gestures in a Dialogue-Based Problem Solving System

A dialogue plays an important role in learning how to solve a problem and form a concept. We are developing a problem solving and knowledge acquisition system based on co-reference between drill texts and dialogue with a teacher, focusing on first-grade mathematics. This paper presents a method of cooperative understanding of utterances and gestures within dialogue. We first describe our system design principles, which provide the basis for the integration of multimodal information during a dialogue. We define a principle of complementarity, explain its implementation, and describe the architecture of the problem solving system. We then show how to integrate our algorithms for utterance and gesture analysis within that software architecture. A feature-based approach is used for gesture recognition, derived from a sequence of images arising during the cooperative analysis of utterances. We conclude with an evaluation of the system against the design principles.     

An Approach to User Interface Specification with Attribute Grammars

An approach to supporting user interfaces using an attribute grammar combined with an event model is described.The main emphasis is how to represent a multi-thread dialogue model in direct manipulation user interfaces.It is shown that control sequence within dialogues,communication with other dialogues, and some computations for applications can be specified with a syntactic and semantic notation.The attribute grammar specification can be implemented using an attribute grammar intepreter embedded in the run-time structure supporting communication,synchronization,and dialogue executon.     

基于多视角对抗学习的开放域对话生成模型

近年来,随着智能家居的普及,对话系统在生活中发挥着越来越重要的作用,基于神经网络构建的生成式对话系统由于其灵活性高受到了许多研究者的关注。以提高生成模型对话的流畅性、上下文相关性为目的,提出基于多视角对抗学习的开放域对话生成模型。其中,模型生成器是基于检索到的相似对话进行改写得到生成的对话;模型的判别器是由两个二分类器共同组成的,该二元判别器分别从句子、对话两个层面多视角地对生成句子进行判别。在中文对话语料上进行实验,该模型在人工评价和自动评测上的得分都高于目前常用的对话生成模型。实验结果表明,利用二元判别器多视角训练可以同时提高生成回复的流畅度和上下文相关性。     

A Dialogue Game Protocol for Agent Purchase Negotiations

We propose a dialogue game protocol for purchase negotiation dialogues which identifies appropriate speech acts, defines constraints on their utterances, and specifies the different sub-tasks agents need to perform in order to engage in dialogues according to this protocol. Our formalism combines a dialogue game similar to those in the philosophy of argumentation with a model of rational consumer purchase decision behaviour adopted from marketing theory. In addition to the dialogue game protocol, we present a portfolio of decision mechanisms for the participating agents engaged in the dialogue and use these to provide our formalism with an operational semantics. We show that these decision mechanisms are sufficient to generate automated purchase decision dialogues between autonomous software agents interacting according to our proposed dialogue game protocol.     

The role of digital artefacts on the interactive whiteboard in supporting classroom dialogue

This paper explores how the interactive whiteboard (IWB) might be harnessed to support student learning through classroom dialogue. This powerful and increasingly prevalent technology opens up opportunities for learners to generate, modify, and evaluate new ideas, through multimodal interaction along with talk. Its use can thereby support rich new forms of dialogue that highlight differences between perspectives, and make ideas and reasoning processes more explicit. The emerging account builds upon Bahktin's conception of dialogue and Wegerif's notion of technology ‘opening up a dialogic space for reflection’, but foregrounds the role of mediating artefacts. Classroom dialogue in the context of IWB use is construed as being facilitated by teachers and learners constructing digitally represented knowledge artefacts together. These visible, dynamic, and constantly evolving resources constitute interim records of activity and act as supportive devices for learners' emerging thinking, rather than finished products of dialogue. This primarily theoretical account is illustrated with examples from case studies of UK classroom practice. Analysing lessons in sequence has illuminated how teachers can exploit the IWB through cumulative interaction with a succession of linked digital resources, and through archiving and revisiting earlier artefacts. The tool thereby helps to support the progression of dialogue over time, across settings and even across learner groups. In sum, the article reframes the notion of dialogue for this new context in which students are actively creating and directly manipulating digital artefacts, and offers some practical examples.     

基于知识增强的开放域多轮对话模型

如何减轻安全回复和重复回复一直是开放域多轮对话模型的两大挑战性难题.然而,现有开放域对话模型往往忽略了对话目标的引导性作用,以及如何在对话历史和对话目标中引入和选择更精确的知识信息.鉴于此,提出基于知识增强的多轮对话模型.所提模型首先将对话历史中实词进行义原及领域词替换,达到消除歧义和丰富对话文本表示的效果.然后将经过知识增强后的对话历史、扩充的三元组世界知识、知识管理和知识拷贝加以集成,以融合知识、词汇、对话历史和对话目标多种信息,生成多样性回复.通过两个国际基准开放域汉语对话语料库上的实验结果及可视化验证所提模型同时在自动评测和人工评测上的有效性.     

Evaluation of a hierarchical reinforcement learning spoken dialogue system

We describe an evaluation of spoken dialogue strategies designed using hierarchical reinforcement learning agents. The dialogue strategies were learnt in a simulated environment and tested in a laboratory setting with 32 users. These dialogues were used to evaluate three types of machine dialogue behaviour: hand-coded, fully-learnt and semi-learnt. These experiments also served to evaluate the realism of simulated dialogues using two proposed metrics contrasted with ‘Precision-Recall’. The learnt dialogue behaviours used the Semi-Markov Decision Process (SMDP) model, and we report the first evaluation of this model in a realistic conversational environment. Experimental results in the travel planning domain provide evidence to support the following claims: (a) hierarchical semi-learnt dialogue agents are a better alternative (with higher overall performance) than deterministic or fully-learnt behaviour; (b) spoken dialogue strategies learnt with highly coherent user behaviour and conservative recognition error rates (keyword error rate of 20%) can outperform a reasonable hand-coded strategy; and (c) hierarchical reinforcement learning dialogue agents are feasible and promising for the (semi) automatic design of optimized dialogue behaviours in larger-scale systems.     

语法和语义相结合的中文对话系统问题理解研究

针对中文口语问句的表达多样性对对话系统问题理解带来的挑战,该文采用“在语法结构之上获取语义知识”的设计理念,提出了一种语法和语义相结合的口语对话系统问题理解方法。首先人工编制了独立于领域和应用方向的语法知识库,进而通过句子压缩模块简化复杂句子,取得结构信息,再进行问题类型模式识别,得到唯一确定问题的语义组织方法、查询策略和应答方式的句型模式。另一方面,根据领域语义知识库,从源句子中提取相应的语义信息,并根据识别到的句型模式所对应的知识组织方法进行语义知识组织,完成对问句的理解。该文的方法被应用到开发的中文手机导购对话系统。测试结果表明,该方法能有效地完成对话流程中的用户问题理解。