Dial4JaCa – A Communication Interface Between Multi-agent Systems and Chatbots

Engelmann, Débora C.; Damasio, Juliana; Krausburg, Tabajara; Borges, Olimar Teixeira; Colissi, Mateus da Silveira; Panisson, Alison R.; Bordini, Rafael H.

doi:10.1007/978-3-030-85739-4_7

Cited by 13 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…When modelling argumentation schemes to this end (explainability), agents are directly able to create, evaluate, and communicate arguments providing explanations for one another or for humans [41]. Templates of the argumentation schemes can be used to provide a translation between the natural language and the computational representation of arguments, allowing for more sophisticated human-agent interactions [51], or even using chatbot technologies [20][21][22]. These research directions are part of our ongoing work.…”

Section: Discussionmentioning

confidence: 99%

A computational model of argumentation schemes for multi-agent systems

Panisson¹,

McBurney²,

Bordini

2021

AAC

View full text Add to dashboard Cite

There are many benefits of using argumentation-based techniques in multi-agent systems, as clearly shown in the literature. Such benefits come not only from the expressiveness that argumentation-based techniques bring to agent communication but also from the reasoning and decision-making capabilities under conditions of conflicting and uncertain information that argumentation enables for autonomous agents. When developing multi-agent applications in which argumentation will be used to improve agent communication and reasoning, argumentation schemes (reasoning patterns for argumentation) are useful in addressing the requirements of the application domain in regards to argumentation (e.g., defining the scope in which argumentation will be used by agents in that particular application). In this work, we propose an argumentation framework that takes into account the particular structure of argumentation schemes at its core. This paper formally defines such a framework and experimentally evaluates its implementation for both argumentation-based reasoning and dialogues.

show abstract

Section: Discussionmentioning

confidence: 99%

A computational model of argumentation schemes for multi-agent systems

Panisson¹,

McBurney²,

Bordini

2021

AAC

View full text Add to dashboard Cite

show abstract

“…Dialogflow sends the user’s request to our multi-agent system. To receive those requests, our system uses an integration between JaCaMo and Dialogflow called Dial4JaCa ( , accessed on 2 March 2022) [ 30 ], which extends the open-source JaCaMo Rest project ( , accessed on 2 March 2022) [ 31 ]. It is represented by the , in Figure 3 .…”

Section: An Approach To Ambient Assisted Livingmentioning

confidence: 99%

Multi-Agent Interaction to Assist Visually-Impaired and Elderly People

Oliveira

Engelmann

Kniest

et al. 2022

IJERPH

Self Cite

View full text Add to dashboard Cite

A voice-controlled smart home system based on conversational agents can address the specific needs of older people, proactively providing support, compensating for cognitive decline, and coping with solitude, among other features. In particular, Multi-Agent Systems (MAS) platforms provide considerable support for complex adaptive systems that are naturally distributed and situated in dynamic environments, such as Ambient intelligence (AmI) applications. Such autonomous intelligent agents are capable of independent reasoning and joint analysis of complex situations to support high-level interaction with humans, besides providing typical characteristics of MAS, such as cooperation and coordinated action. In this context, we developed an approach using a MAS previously evaluated for visually impaired users, where most of the system’s functionalities are also helpful for the elderly. Our methodology is based on the four steps of the interactive design process. As a result, we determined that our approach has elements that allow for natural interaction with users, and we identified and discussed improvements and new features for future work. We believe that our findings can point to directions for building AmI systems that are capable of more natural interaction with users.

show abstract

“…In this paper, we use a scenario of bed allocation in hospitals, based on the work reported in [10,11,8,12], in order to exemplify how we have built our approach for explaining semantic reasoning using argumentation. Bed allocation is a challenge hospitals face since hospital beds are scarce, and when poorly managed, it can generate long lines and chaos in emergency rooms [19].…”

Section: Scenariomentioning

confidence: 99%

“…Considering that MAS can be powered by different artificial intelligence techniques, they are suitable to deal with complex problems like bed allocation in hospitals. Thanks to recent developments, MAS are equipped with communication in natural language [10,9] and ontological reasoning [14].…”

Section: Scenariomentioning

confidence: 99%

“…Below, we have an example of dialogue that occurs in the multi-agent application developed, in which a human operator tries to allocate a patient named patient2 to the bed 101b; however, bed 101b is considered unsuitable for that patient given the hospital rules modelled in the domain-specific ontology of that application. Thus, the agent (software agent) responsible to assist the bed allocation in the multi-agent application opens a dialogue with the human operator to inform that bed is not suitable for that patient, later explaining why it is not suitable: This dialogue in natural language is resulting from the approach we will present in this paper, combined with other technologies: (i) Dial4JaCa 6 [10], which allows the integration between chatbot technologies and MAS, and it is used to identify users' intentions and to extract entities from natural language inputs as well as to provide responses to users in natural language; and (ii) an interface between MAS and ontologies [14], which allows extending the agents' belief bases with semantic technologies. While Dial4JaCa represents an important component in the multi-agent application developed, which provides an interactive interface with human users, in this work we are going to focus only on the the components necessary to present our approach, namely the interface between ontologies and MAS.…”

Section: Scenariomentioning

confidence: 99%

See 1 more Smart Citation

Explaining Semantic Reasoning Using Argumentation

Ferreira¹,

Panisson²,

Engelmann

et al. 2022

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Multi-Agent Systems (MAS) are popular because they provide a paradigm that naturally meets the current demand to design and implement distributed intelligent systems. When developing a multiagent application, it is common to use ontologies to provide the domainspecific knowledge and vocabulary necessary for agents to achieve the system goals. In this paper, we propose an approach in which agents can query semantic reasoners and use the received inferences to build explanations for such reasoning. Also, thanks to an internal representation of inference rules used to build explanations, in the form of argumentation schemes, agents are able to reason and make decisions based on the answers from the semantic reasoner. Furthermore, agents can communicate the built explanation to other agents and humans, using computational or natural language representations of arguments. Our approach paves the way towards multi-agent systems able to provide explanations from the reasoning carried out by semantic reasoners.

show abstract

Dial4JaCa – A Communication Interface Between Multi-agent Systems and Chatbots

Cited by 13 publications

References 15 publications

A computational model of argumentation schemes for multi-agent systems

A computational model of argumentation schemes for multi-agent systems

Multi-Agent Interaction to Assist Visually-Impaired and Elderly People

Explaining Semantic Reasoning Using Argumentation

Contact Info

Product

Resources

About