An inquiry dialogue system

The majority of existing work on agent dialogues considers negotiation, persuasion or deliberation dialogues; we focus on inquiry dialogues, which allow agents to collaborate in order to find new knowledge. We present a general framework for representing dialogues and give the details necessary to generate two subtypes of inquiry dialogue that we define: argument inquiry dialogues allow two agents to share knowledge to jointly construct arguments; warrant inquiry dialogues allow two agents to share knowledge to jointly construct dialectical trees (essentially a tree with an argument at each node in which a child node is a counter argument to its parent). Existing inquiry dialogue systems only model dialogues, meaning they provide a protocol which dictates what the possible legal next moves are but not which of these moves to make. Our system not only includes a dialogue-game style protocol for each subtype of inquiry dialogue that we present, but also a strategy that selects exactly one of the legal moves to make. We propose a benchmark against which we compare our dialogues, being the arguments that can be constructed from the union of the agents’ beliefs, and use this to define soundness and completeness properties that we show hold for all inquiry dialogues generated by our system.     

A Geometric Semantics for Dialogue Game Protocols for Autonomous Agent Interactions

Formal dialogue games studied by philosophers since the time of Aristotle have recently found application in Artificial Intelligence as the basis for protocols for interactions between autonomous software agents. For instance, game protocols have been proposed for agent dialogues involving team formation, persuasion, negotiation and deliberation. There is yet, however, no formal, mathematical theory of dialogue game protocols with which to compare two protocols or to study their formal properties. In this paper,¹ we present preliminary work towards such a theory, in which we develop a geometric semantics for these protocols and, with it, define a notion of equivalence between two protocols. We then demonstrate an algebraic property of protocol equivalence, and use this to show the non-equivalence of two similar generic protocols. We also explore the relationship between finite and infinite dialogues, motivated by the Ehrenfeucht-Fraïssé games of model theory. Our results have implications for the design and evaluation of agent dialogue-game protocols.     

Games That Agents Play: A Formal Framework for Dialogues between Autonomous Agents

We present a logic-based formalism for modeling ofdialogues between intelligent and autonomous software agents,building on a theory of abstract dialogue games which we present.The formalism enables representation of complex dialogues assequences of moves in a combination of dialogue games, and allowsdialogues to be embedded inside one another. The formalism iscomputational and its modular nature enables different types ofdialogues to be represented.     

Dialogue games that agents play within a society

Human societies have long used the capability of argumentation and dialogue to overcome and resolve conflicts that may arise within their communities. Today, there is an increasing level of interest in the application of such dialogue games within artificial agent societies. In particular, within the field of multi-agent systems, this theory of argumentation and dialogue games has become instrumental in designing rich interaction protocols and in providing agents with a means to manage and resolve conflicts. However, to date, much of the existing literature focuses on formulating theoretically sound and complete models for multi-agent systems. Nonetheless, in so doing, it has tended to overlook the computational implications of applying such models in agent societies, especially ones with complex social structures. Furthermore, the systemic impact of using argumentation in multi-agent societies and its interplay with other forms of social influences (such as those that emanate from the roles and relationships of a society) within such contexts has also received comparatively little attention. To this end, this paper presents a significant step towards bridging these gaps for one of the most important dialogue game types; namely argumentation-based negotiation (ABN). The contributions are three fold. First, we present a both theoretically grounded and computationally tractable ABN framework that allows agents to argue, negotiate, and resolve conflicts relating to their social influences within a multi-agent society. In particular, the model encapsulates four fundamental elements: (i) a scheme that captures the stereotypical pattern of reasoning about rights and obligations in an agent society, (ii) a mechanism to use this scheme to systematically identify social arguments to use in such contexts, (iii) a language and a protocol to govern the agent interactions, and (iv) a set of decision functions to enable agents to participate in such dialogues. Second, we use this framework to devise a series of concrete algorithms that give agents a set of ABN strategies to argue and resolve conflicts in a multi-agent task allocation scenario. In so doing, we exemplify the versatility of our framework and its ability to facilitate complex argumentation dialogues within artificial agent societies. Finally, we carry out a series of experiments to identify how and when argumentation can be useful for agent societies. In particular, our results show: a clear inverse correlation between the benefit of arguing and the resources available within the context; that when agents operate with imperfect knowledge, an arguing approach allows them to perform more effectively than a non-arguing one; that arguing earlier in an ABN interaction presents a more efficient method than arguing later in the interaction; and that allowing agents to negotiate their social influences presents both an effective and an efficient method that enhances their performance within a society.     

Negotiating Dialogue Games

Recently in the field of agent communication, many authors have adopted the view of interaction as a joint activity regulated by means of dialogue games. It is argued in particular that this approach should increase the flexibility of dialogues by allowing a variety of game compositions. In this research note, we present a framework suited to this feature. A preliminary attempt to capture the negotiation phase (which allows agents to agree upon the dialogue game currently regulating their conversation) is discussed.     

Towards a multi-agent system for regulated information exchange in crime investigations

This paper outlines a multi-agent architecture for regulated information exchange of crime investigation data between police forces. Interactions between police officers about information exchange are analysed as negotiation dialogues with embedded persuasion dialogues. An architecture is then proposed consisting of two agents, a requesting agent and a responding agent, and a communication language and protocol with which these agents can interact to promote optimal information exchange while respecting the law. Finally, dialogue policies are defined for the individual agents, specifying their behaviour within a negotiation. Essentially, when deciding to accept or reject an offer or to make a counteroffer, an agent first determines whether it is obligatory or permitted to perform the actions specified in the offer. If permitted but not obligatory, the agent next determines whether it is in his interest to accept the offer.     

Dialogue Games for Inconsistent and Biased Information

In this article, a dialogue game is presented in which coherent conversational sequences with inconsistent and biased information are described at the speech act level. Inconsistent and biased information is represented with bilattice structures, and based on these bilattice structures, a multi-valued logic is defined that makes it possible to describe a dialogue game in which agents can communicate about their cognitive states with inconsistent and biased information. A dialogue game is formalized by, first, defining the agent's cognitive state as a set of multi-valued theories, second, by defining the dialogue rules that prescribe permissible communicative acts based on the agent's cognitive state, and last, by defining update rules that change the agent's cognitive state as a result of communicative acts. We show that an example dialogue with inconsistent and biased information can be derived from our dialogue game.     

Subjective logic and arguing with evidence

This paper introduces a subjective logic based argumentation framework primarily targeted at evidential reasoning. The framework explicitly caters for argument schemes, accrual of arguments, and burden of proof; these concepts appear in many types of argument, and are particularly useful in dialogues revolving around evidential reasoning. The concept of a sensor is also useful in this domain, representing a source of evidence, and is incorporated in our framework. We show how the framework copes with a number of problems that existing frameworks have difficulty dealing with, and how it can be situated within a simple dialogue game. Finally, we examine reasoning machinery that enables an agent to decide what argument to advance with the goal of maximising its utility at the end of a dialogue.     

Dialogue patterns—A visual language for dynamic dialogue

A dynamic dialogue is a conversation in which each participant alternately selects remarks based on a changing world state and in which each remark can change the world state. Dynamic dialogues happen frequently as conversations between a player character (PC) and a non-player character (NPC) in a computer game. When it is the PC's turn to speak, the current game state is used to filter the static set of remarks available to the PC to a contextually appropriate subset that is made available to the player. Selecting a PC remark then leads to a candidate set of NPC remarks as appropriate responses to the PC. The world state is used to filter this set of remarks to a single remark, which is used by the NPC as the reply. To construct a dynamic dialogue, an author must not only create the remarks, but also write the code that determines which remarks are available to both participants at any point in the dialogue. We present “generative dialogue patterns” as a new visual language for designing dynamic dialogues and generating the program code that is necessary to select the appropriate remarks during the dialogue. We use a case study from the computer games domain to evaluate the effectiveness of generative dialogue patterns.     

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.     

Cooperative requests and replies in a collaborative dialogue model

In this paper, we present a computational model of dialogue, and an underlying theory of action, which supports the representation of, reasoning about and execution of communicative and non-communicative actions. This model rests on a theory of collaborative discourse, and allows for cooperative human–machine communication in written dialogues. We show how cooperative behaviour, illustrated by the analysis of a dialogue corpus and formalized by an underlying theory of cooperation, is interpreted and produced in our model. We describe and illustrate in detail the main algorithms used to model the reasoning processes necessary for interpretation, planning, generation, as well as for determining which actions to perform and when. Finally, we present our implemented system.Our data are drawn from a corpus of human–human dialogues, selected and transcribed from a day-long recording of phone calls at a phone desk in an industrial setting (Castaing, 1993). We present an analysis of this corpus, focusing on dialogues which require, in order to succeed, helpful behaviour on the part of both the caller and the operator.The theoretical framework of our model rests on the theory of collaborative discourse developed by Grosz and Sidner (1986, 1990), Grosz and Kraus (1993, 1996), and further extended by Lochbaum (1994, 1995). An important objective guiding the design of our dialogue model was to allow the agent being modelled to interpret and manifest a type of cooperative behaviour which follows Grosz and Kraus's formalization of the commitment of each collaborative agent towards the actions of the other collaborative agents. The model we propose extends Lochbaum's approach to discourse processing in extending her interpretation algorithm to allow for the treatment of a wider range of dialogues, and in providing an algorithm of task advancement which guides the generation process and allows for the interleaving of execution and planning, thereby facilitating cooperation among agents. The cooperative behaviour of the agent being modelled rests on the use of communicative actions allowing agents to share additional knowledge and assist each other in performing their actions.     

Inter-agent Dialogues in Electronic Marketplaces

This paper presents an overall framework for carrying out different types of dialogues between intelligent and autonomous agents acting in an electronic marketplace. Such dialogues take place during various commercial transactions concerning requests and offers of products and services. The proposed dialogue framework has been adopted in the communication and collaboration protocols of an already implemented system, which enables buyers and sellers delegate a variety of tasks to their personal agents. Much attention has been paid to the personalization of collaborative agents, which may permanently live and interact in the market representing their owners' interests. Our overall approach builds on a modular decomposition of the agents involved, and a formal and operational modeling of the associated dialogues. Features of our framework are demonstrated through an illustrative example of dialogues deployed during interagent transactions on the establishment of a combined reservation for dinner and a movie. The main contribution of this work is that the proposed framework is capable to represent disparate dialogues taking place among agents having adopted diverse strategies for carrying out e-commerce transactions.     

A Dialogue Game Protocol for Multi-Agent Argument over Proposals for Action

We present the syntax and semantics for a multi-agent dialogue game protocol which permits argument over proposals for action. The protocol, called the Persuasive Argument for Multiple Agents (PARMA) Protocol, embodies an earlier theory by the authors of persuasion over action which enables participants to rationally propose, attack, and defend, an action or course of actions (or inaction). We present an outline of both an axiomatic and a denotational semantics, and discuss implementation of the protocol, in the context of both human and artificial agents.     

Evaluating spoken dialogue agents with PARADISE: Two case studies

This paper presents PARADISE (PARAdigm for DIalogue System Evaluation), a general framework for evaluating and comparing the performance of spoken dialogue agents. The framework decouples task requirements from an agent's dialogue behaviours, supports comparisons among dialogue strategies, enables the calculation of performance over subdialogues and whole dialogues, specifies the relative contribution of various factors to performance, and makes it possible to compare agents performing different taks by normalizing for task complexity. After presenting PARADISE, we illustrate its application to two different spoken dialogue agents. We show how to derive a performance function for each agent and how to generalize results across agents. We then show that once such a performance function has been derived, it can be used both for making predictions about future versions of an agent, and as feedback to the agent so that the agent can learn to optimize its behaviour based on its experiences with users over time.     

DIAGAL: An Agent Communication Language Based on Dialogue Games and Sustained by Social Commitments

In recent years, social commitment based approaches have been proposed to solve problems issuing from previous mentalistic based semantics for agent communication languages. This paper follows the same line of thought since it presents the latest version of our dialogue game based agent communication language – DIAlogue-Game based Agent Language (DIAGAL) – which allows agents to manipulate the public layer of social commitments through dialogue, by creating, canceling and updating their social commitments. To make apparent such commitments, we consider here Agent Communication Language (ACL) from the dialectic point of view, where agents “play a game” based on commitments. Such games based on commitments are incorporated in the DIAGAL language, which has been developed having in mind the following questions: (a) What kind of structure does the game have? How are rules specified within the game? (b) What kind of games compositions are allowed? (c) How do participants in conversations reach agreement on the current game? How are games opened or closed? Using such games we show how we can study the commitments dynamic to model agent dialogue and we present metrics that can be used to evaluate the quality of a dialogue between agents. Next, we use an example (summer festival organization) to show how DIAGAL can be used in analyzing and modeling automated conversations in offices. Finally, we present the results and analysis of the summer festival simulations that we realized through our dialogue game simulator (DGS).     

Meaning and Dialogue Coherence: A Proof-theoretic Investigation

This paper presents a novel proof-theoretic account of dialogue coherence. It focuses on an abstract class of cooperative information-oriented dialogues and describes how their structure can be accounted for in terms of a multi-agent hybrid inference system that combines natural deduction with information transfer and observation. We show how certain dialogue structures arise out of the interplay between the inferential roles of logical connectives (i.e., sentence semantics), a rule for transferring information between agents, and a rule for information flow between agents and their environment. The order of explanation is opposite in direction to that adopted in game-theoretic semantics, where sentence semantics (or a notion of valid inference) is derived from winning dialogue strategies. That approach and the current one may, however, be reconcilable, since we focus on cooperative dialogue, whereas the game-theoretic tradition concentrates on adversarial dialogue. An erratum to this article can be found at     

Dialogues in support of qualitative reasoning

Abstract Do students always interact with computers reflectively on tasks and improve qualitative reasoning? It seems that students often manipulate software without changing existing conceptions or exploring the implications of their conceptions to generate deeper explanations. This undermines the educational value of such interactions — though dialogue with a peer or adult can make the interaction more valuable. However, it is uncertain when and how such dialogues work. If high quality educational interactions with computers are to take place, then it is necessary to understand the situations in which particular dialogue forms are effective and to find ways of modelling these. In this paper a framework for the design of such interactions is proposed based on a dialogue analysis that employs transactional analysis and logical dialogue game theory. The framework is applied to a medical (simulation-based) learning context to illustrate how it may enhance interactions with such systems.     

Applying game theory mechanisms in open agent systems with complete information

Game theory is a popular tool for designing interaction protocols for agent systems. It is currently not clear how to extend this to open agent systems. By “open” we mean that foreign agents will be free to enter and leave different systems at will. This means that agents will need to be able to work with previously unseen protocols. There does not yet exist any agreement on a standard way in which such protocols can be specified and published. Furthermore, it is not clear how an agent could be given the ability to use an arbitrary published protocol; the agent would need to be able to work out a strategy for participation. To address this we propose a machine readable language in which a game theory mechanism can be written in the form of an agent interaction protocol. This language allows the workings of the protocol to be made public so that agents can inspect it to determine its properties and hence their best strategy. Enabling agents to automatically determine the game theoretic properties of an arbitrary interaction protocol is difficult. Rather than requiring agents to find the equilibrium of a game, we propose that a recommended equilibrium will be published along with the protocol; agents can then check the recommendation to decide if it is indeed an equilibrium. We present an algorithm for this decision problem. We also develop an equilibrium which simplifies the complexity of the checking problem, while still being robust to unilateral deviations.     

Collective Decision-Making Process to Compose Divergent Interests and Perspectives

We propose in this paper DIAL, a framework for inter-agents dialogue, which formalize a collective decision-making process to compose divergent interests and perspectives. This framework bounds a dialectics system in which argumentative agents play and arbitrate to reach an agreement. For this purpose, we propose an argumentation-based reasoning to manage the conflicts between arguments having different strengths for different agents. Moreover, we propose a model of argumentative agents which justify the hypothesis to which they commit and take into account the commitments of their interlocutors according to their reputations. In the scope of our dialectics system, a third agent is responsible of the final decision outcome which is taken by resolving the conflict between two players according to their competences and the advanced arguments.