Dialog Agents


A dialog agent, also known as a conversational agent or chatbot, is a computer program designed to simulate conversation with human users. Dialog agents are often used in customer service and support environments, where they can provide quick, automated responses to common questions and requests. They can also be used in other areas, such as online education or entertainment, to provide information and engage with users in a natural language conversation.

  • Conversation agent, or conversational agent, is a software program that is designed to engage in natural language conversations with humans. Conversation agents can be used for a wide range of purposes, including providing customer service, answering questions, and assisting with tasks.
  • Dialog agent, or dialogue agent, is a software program that is designed to engage in dialogues with humans. Dialog agents can be used for a wide range of purposes, including providing customer service, answering questions, and assisting with tasks.


  • Emotion Awareness in Dialog Agents (2011)

See also:

Autonomous Agents, Natural Language & Dialog Systems | Conversational Agents | Language-independent & Dialog Systems

Learning cooperative visual dialog agents with deep reinforcement learning
A Das, S Kottur, JMF Moura, S Lee… – arXiv preprint arXiv …, 2017 – openaccess.thecvf.com
Abstract We introduce the first goal-driven training for visual question answering and dialog agents. Specifically, we pose a cooperative ‘image guessing’game between two agents–Q-BOT and A-BOT–who communicate in natural language dialog so that Q-BOT can select an

End-to-end reinforcement learning of dialogue agents for information access
B Dhingra, L Li, X Li, J Gao, YN Chen, F Ahmed… – arXiv preprint arXiv …, 2016 – arxiv.org
Abstract: This paper proposes\emph {KB-InfoBot}—a dialogue agent that provides users with an entity from a knowledge base (KB) by interactively asking for its attributes. All components of the KB-InfoBot are trained in an end-to-end fashion using reinforcement

Aida: Artificial intelligent dialogue agent
RE Banchs, R Jiang, S Kim, A Niswar… – Proceedings of the …, 2013 – aclweb.org
Abstract This demo paper describes our Artificial Intelligent Dialogue Agent (AIDA), a dialogue management and orchestration platform under development at the Institute for Infocomm Research. Among other features, it integrates different human-computer

R-cube: a dialogue agent for restaurant recommendation and reservation
S Kim, RE Banchs – Signal and Information Processing …, 2014 – ieeexplore.ieee.org
This paper describes a hybrid dialogue system for restaurant recommendation and reservation. The proposed system combines rule-based and data-driven components by using a flexible architecture aiming at diminishing error propagation along the different steps

Machine-learned ranking based non-task-oriented dialogue agent using twitter data
M Koshinda, M Inaba… – … Agent Technology (WI-IAT) …, 2015 – ieeexplore.ieee.org
This paper describes a method for developing a non-task-oriented dialogue agent (also called chat-oriented or conversational dialogue agents) that can cover broad range of topics. Our method extracts a topic from a user’s utterance and acquires candidate utterances that

Metacognitive guidance in a dialog agent
E McNany, D Josyula, M Cox, M Paisner… – Proceedings of the Fifth …, 2013 – cs.umd.edu
Abstract—The paper discusses the benefits of metacognitive guidance for a natural language dialog agent. These capabilities may be included directly in the agent or through a general purpose external module. We report on the specific case of handling pause time in

Evaluating persuasion strategies and deep reinforcement learning methods for negotiation dialogue agents
S Keizer, M Guhe, H Cuayáhuitl, I Efstathiou… – Proceedings of the 15th …, 2017 – aclweb.org
Abstract In this paper we present a comparative evaluation of various negotiation strategies within an online version of the game “Settlers of Catan”. The comparison is based on human subjects playing games against artificial game-playing agents (‘bots’) which implement

An Intelligent Dialogue Agent for the IoT Home.
H Jeon, HR Oh, I Hwang, J Kim – AAAI Workshop: Artificial Intelligence …, 2016 – aaai.org
Abstract In this paper, we propose an intelligent dialogue agent for the IoT home. The goal of the proposed system is to efficiently control IoT devices with natural spoken dialogue. This system is made up of the following components: Spoken Language Understanding for

A framework for multilingual real-time spoken dialogue agents
A Jordan, K Araki – … and Technology (iCAST), 2014 IEEE 6th …, 2014 – ieeexplore.ieee.org
In this paper, we propose a framework for a spoken dialogue agent that is not dependent on any specific language; it takes some dialogues and sentences as training sets and uses them to acquire knowledge about the target language, then it uses this knowledge to

Measuring and analyzing agents’ uncertainty in argumentation-based negotiation dialogue games
O Marey, J Bentahar, R Dssouli, M Mbarki – Expert Systems with …, 2014 – Elsevier
Abstract Nowadays, multiagent systems have become a widely used technology in everyday life, and many authors have adopted the view of communication or interaction between agents as a joint activity regulated by means of dialogue games. Dialogue games are a set

A configurable conversational agent to trigger students’ productive dialogue: a pilot study in the CALL domain
S Tegos, S Demetriadis, T Tsiatsos – International Journal of Artificial …, 2014 – Springer
Abstract Conversational agents constitute a specific type of ITSs that has been reportedly proven successful in helping students in one-to-one settings, while recently their impact has also been explored in computer-supported collaborative learning (CSCL). In this work, we

Single-agent vs. multi-agent techniques for concurrent reinforcement learning of negotiation dialogue policies
K Georgila, C Nelson, D Traum – … of the 52nd Annual Meeting of the …, 2014 – aclweb.org
Abstract We use single-agent and multi-agent Reinforcement Learning (RL) for learning dialogue policies in a resource allocation negotiation scenario. Two agents learn concurrently by interacting with each other without any need for simulated users (SUs) to

An automatic dialog simulation technique to develop and evaluate interactive conversational agents
D Griol, J Carbó, JM Molina – Applied Artificial Intelligence, 2013 – Taylor & Francis
During recent years, conversational agents have become a solution to provide straightforward and more natural ways of retrieving information in the digital domain. In this article, we present an agent-based dialog simulation technique for learning new dialog

What do learners and pedagogical agents discuss when given opportunities for open-ended dialogue?
G Veletsianos, GS Russell – Journal of Educational …, 2013 – journals.sagepub.com
Researchers claim that pedagogical agents engender opportunities for social learning in digital environments. Prior literature, however, has not thoroughly examined the discourse between agents and learners. To address this gap, we analyzed a data corpus of

Learning symmetric collaborative dialogue agents with dynamic knowledge graph embeddings
H He, A Balakrishnan, M Eric, P Liang – arXiv preprint arXiv:1704.07130, 2017 – arxiv.org
Abstract: We study a symmetric collaborative dialogue setting in which two agents, each with private knowledge, must strategically communicate to achieve a common goal. The open-ended dialogue state in this setting poses new challenges for existing dialogue systems. We

Natural Language Does Not Emerge’Naturally’in Multi-Agent Dialog
S Kottur, JMF Moura, S Lee, D Batra – arXiv preprint arXiv:1706.08502, 2017 – arxiv.org
Abstract: A number of recent works have proposed techniques for end-to-end learning of communication protocols among cooperative multi-agent populations, and have simultaneously found the emergence of grounded human-interpretable language in the

Co-constructing grounded symbols—feedback and incremental adaptation in human–agent dialogue
H Buschmeier, S Kopp – KI-Künstliche Intelligenz, 2013 – Springer
Abstract Grounding in dialogue concerns the question of how the gap between the individual symbol systems of interlocutors can be bridged so that mutual understanding is possible. This problem is highly relevant to human–agent interaction where mis-or non-

Exploiting knowledge base to generate responses for natural language dialog listening agents
S Han, J Bang, S Ryu, GG Lee – … Group on Discourse and Dialogue, 2015 – aclweb.org
Abstract We developed a natural language dialog listening agent that uses a knowledge base (KB) to generate rich and relevant responses. Our system extracts an important named entity from a user utterance, then scans the KB to extract contents related to this entity. The

An I-POMDP based multi-agent architecture for dialogue tutoring
F Wang – International Conference on Advanced ICT and …, 2013 – atlantis-press.com
Abstract Dialogue systems have been widely considered as useful tools for education. The challenging tasks in developing a dialogue tutoring system include correctly interpreting student input and choosing appropriate responses. In this paper, we present a two-agent

Dialogue enabling speech-to-text user assistive agent with auditory perceptual beamforming for hearing-impaired
S Lee, S Kang, H Ko, J Yoon… – … Electronics (ICCE), 2013 …, 2013 – ieeexplore.ieee.org
A novel approach for assisting effective bidirectional communication of intentions between people of normal hearing and hearing-impaired is presented in this paper. In particular, we demonstrate the intelligent hearing assistive utility by incorporating a speech-to-text

Learning non-cooperative behaviour for dialogue agents
I Efstathiou, O Lemon – Proceedings of the Twenty-first European …, 2014 – dl.acm.org
Abstract Non-cooperative dialogue behaviour for artificial agents (eg deception and information hiding) has been identified as important in a variety of application areas, including education and healthcare, but it has not yet been addressed using modern

Effects of interface interactivity on collecting language data to power dialogue agents
HC Wang, TH Yeo, HH Lee, AJ Huang… – Proceedings of the …, 2014 – dl.acm.org
Abstract Conversation is one of the easiest modes of communication. Interactive dialogue agents are promising natural interfaces for people to interact with machines. The building of these agents, however, suffers from lacking quality language data for supporting the

Development and evaluation of spoken dialog systems with one or two agents through two domains
Y Todo, R Nishimura, K Yamamoto… – … , Speech and Dialogue, 2013 – Springer
Abstract Almost all current spoken dialog systems treat dialog as that where a single user talks to an agent. On the other hand, we set out to investigate a multiparty dialog system that deals with two agents and a single user. We developed a three person (one user and two

Ethics for a combined human-machine dialogue agent
R Artstein, K Silver – … and Moral Considerations in Non-Human Agents, 2016 – aaai.org
Abstract We discuss philosophical and ethical issues that arise from a dialogue system intended to portray a real person, using recordings of the person together with a machine agent that selects recordings during a synchronous conversation with a user. System output

Empirical specification of dialogue games for an interactive agent
GD Duplessis, N Chaignaud, JP Kotowicz… – … Agents and Multi-Agent …, 2013 – Springer
Abstract This article addresses the challenge of designing the communicative behaviour of an agent interacting with humans. We present a data-driven methodology based on the production of a matrix representation of a corpus from which we extract dialogue patterns.

Korean anaphora recognition system to develop healthcare dialogue-type agent
J Yang, Y Lee – Healthcare informatics research, 2014 – synapse.koreamed.org
Objectives Anaphora recognition is a process to identify exactly which noun has been used previously and relates to a pronoun that is included in a specific sentence later. Therefore, anaphora recognition is an essential element of a dialogue agent system. In the current

Statistical response method and learning data acquisition using gamified crowdsourcing for a non-task-oriented dialogue agent
M Inaba, N Iwata, F Toriumi, T Hirayama… – … Conference on Agents …, 2014 – Springer
Abstract This paper presents a proposal of a construction method for non-task-oriented dialogue agents (chatbots) that are based on the statistical response method. The method prepares candidate utterances in advance. From the data, it learns which utterances are

A personal agents hybrid architecture for question answering featuring social dialog
M Coronado, CA Iglesias… – Innovations in Intelligent …, 2015 – ieeexplore.ieee.org
There exists a growing trend in using NLIs (Natural Language Interfaces) that ranges from research to commercial products. Conversational agents beneath these interfaces have become more sophisticated, being able to either perform a task in behalf of the user or give

Multimodal fusion in human-agent dialogue
E André, JC Martin, F Lingenfelser… – Coverbal Synchrony in …, 2014 – books.google.com
Sophisticated fusion techniques are an essential component of any multimodal system. Historically, systems aimed at analyzing the semantics of multimodal commands and typically investigated a combination of pointing and drawing gestures and speech. The most

Shifting the load: A peer dialogue agent that encourages its human collaborator to contribute more to problem solving
C Howard, P Jordan, B Di Eugenio, S Katz – International Journal of …, 2017 – Springer
Abstract Despite a growing need for educational tools that support students at the earliest phases of undergraduate Computer Science (CS) curricula, relatively few such tools exist–the majority being Intelligent Tutoring Systems. Since peer interactions more readily give

Real-time Language-Independent Algorithm for Dialogue Agents
A JORDAN, K ARAKI – ?????, 2016 – jstage.jst.go.jp
?? This article presents an innovative dialogue agent designed for textual casual chatting, which can handle any language. The system acquires knowledge from a non-annotated corpus and then represents all the language aspects as a graph. Using graph traversal, the

Predicting Dialogue Acts for Intelligent Virtual Agents with Multimodal Student Interaction Data.
W Min, JB Wiggins, L Pezzullo, AK Vail, KE Boyer… – EDM, 2016 – cise.ufl.edu
ABSTRACT Recent years have seen a growing interest in intelligent gamebased learning environments featuring virtual agents. A key challenge posed by incorporating virtual agents in game-based learning environments is dynamically determining the dialogue moves they

A new dialogue strategy in multi-agent systems
A Beigi, N Mozayani – Journal of Intelligent & Fuzzy Systems, 2014 – content.iospress.com
Abstract For establishing communications and modeling a framework for dialogue between intelligent agents, it is beneficial to have a well-defined strategy. In a dialogue run, the strategies are the manners to achieve the agents’ goals by selecting the best option between

Perception of artificial agents and utterance friendliness in dialogue
S Griffiths, FA Eyssel, A Philippsen… – Proceedings of the …, 2015 – pub.uni-bielefeld.de
Abstract The present contribution investigates the construction of dialogue structure for the use in human-machine interaction especially for robotic systems and embodied conversational agents. We are going to present a methodology and findings of a pilot study

Data-driven dialogue systems for social agents
KK Bowden, S Oraby, A Misra, J Wu, S Lukin – arXiv preprint arXiv …, 2017 – arxiv.org
Abstract: In order to build dialogue systems to tackle the ambitious task of holding social conversations, we argue that we need a data driven approach that includes insight into human conversational chit chat, and which incorporates different natural language

Human agent interfaces as a key element for the dialog between human crews and cognitive automation
Y Brand, A Schulte – AIAA Infotech@ aerospace, 2015 – arc.aiaa.org
This article discusses the role of a human agent interface (HAI) for the dialog between aircraft cockpit crews and a cognitive and adaptive assistant system. The design guideline for the assistant system is presented in order to define the requirements, which the interface

Towards agent dialogue as a tool for capturing software design discussions
E Black, P McBurney, S Zschaler – … on Theorie and Applications of Formal …, 2013 – Springer
Abstract Software design is an important creative step in the engineering of software systems, yet we know surprisingly little about how humans actually do it. While it has been argued before that there is a need for formal frameworks to help capture design dialogues in

A novel description language for two-agent dialogue games
A Sawicka, M Kacprzak, A Zbrzezny – International Joint Conference on …, 2017 – Springer
Abstract Every day we use protocols unconsciously during the conversations and the ability to abide by them is an important part of our communication skills (eg questioning the question is neither contributing to the conversation nor polite). The protocols can support

Chat-like spoken dialog system for a multi-party dialog incorporating two agents and a user
R Nishimura, Y Todo, K Yamamoto… – Proceedings of …, 2013 – slp.cs.tut.ac.jp
Abstract: Almost all current spoken dialog systems have treated dialog that one user talks with one agent. In this paper, to achieve the multi-party conversation (polylogue, many users/agents participate conversation), the number of system agents is increased. Three

Development and evaluation of spoken dialog systems with one or two agents.
Y Todo, R Nishimura, K Yamamoto… – …, 2013 – pdfs.semanticscholar.org
Abstract Almost all current spoken dialog systems treat dialog as that where a single user talks to an agent. We, on the other hand, set out to investigate a multiparty dialog system that deals with two agents and a single user. We developed a three person (one user and two

Argumentative dialogue revision in multi-agent system
YO Yang, Y Deng – … Science & Education (ICCSE), 2015 10th …, 2015 – ieeexplore.ieee.org
Most of the traditional belief revisions were built on a completely reliable set of static beliefs between the believable intelligent agents, which are unrealistic due to their inability to identify the credibility of faith. Argumentative dialogue is a basic method for intelligent agents

Dialogue and social behaviour of agents in games
EOC Gutierrez, O de Troyer – The Computer Games Journal, 2014 – Springer
Abstract As games keep evolving and improving in areas such as graphics, audio and physics, game players also expect the games to have believable agents. Many games have been criticised by players because of repeated dialogues; or because of the developers’

Extension with intelligent agents for the spoken dialogue system for smartphones
T Uchiya, R Nakano, D Yamamoto… – … (GCCE), 2015 IEEE …, 2015 – ieeexplore.ieee.org
MMDAgent has been proposed as a voice dialogue system capable of voice interaction in real time with 3D character. In order to improve the convenience by enlarging the operating environment, the” Smart Meichan” has been proposed transplanted with MMDAgent on

flexdiam–Flexible dialogue management for incremental interaction with virtual agents (demo paper)
R Yaghoubzadeh, S Kopp – … Conference on Intelligent Virtual Agents, 2016 – Springer
Abstract We present a demonstration system for incremental spoken human–machine dialogue for task-centric domains that includes a controller for verbal and nonverbal behavior for virtual agents. The dialogue management components can handle uncertainty

Interactive browsing agent for the novice user with selective information in dialog
T Yonezawa, Y Nakatani, N Yoshida… – Soft Computing and …, 2014 – ieeexplore.ieee.org
This paper introduces the Eli-Taso system, an interactive agent that dialogically conveys news and topics corresponding to the user’s reactions. News and BBS contents have hierarchical data structures by categories. In order to support Web browsing without

Multi-agent learning in multi-domain spoken dialogue systems
M Gašic, N Mrkšic, LR Barahona… – … Proceedings of the …, 2015 – pdfs.semanticscholar.org
Abstract The use of a committee of dialogue policies has been shown to be particularly beneficial for adaptation in multi-domain dialogue systems. In this model, each domain is represented by a committee member and the committee collaboratively decides which

… : A Dialogue between the Public and the Private in Maharaja Kumari Binodini Devi’s Boro Sahib Ongbi Sanatombi (The Princess and the Political Agent)
N Thoudam – Indian Journal of Gender Studies, 2016 – journals.sagepub.com
Conventionally, the focus of history writing is ‘public’lives and ‘public’events. Maharaja Kumari Binodini Devi’s Boro Sahib Ongbi Sanatombi (The princess and the political agent, 1976), however, inverts this dominant tradition, diverting the attention of the reader from the

A modular, multimodal open-source virtual interviewer dialog agent
K Cofino, V Ramanarayanan, P Lange… – Proceedings of the 19th …, 2017 – dl.acm.org
Abstract We present an open-source multimodal dialog system equipped with a virtual human avatar interlocutor. The agent, rigged in Blender and developed in Unity with WebGL support, interfaces with the HALEF open-source cloud-based standard-compliant dialog

Spoken Dialogue Agent System for Writing Resumes while Practicing Job Interviews
K Sumi, K Morita – Theory and Practice of Computation: Proceedings …, 2017 – World Scientific
We propose a system that automatically generates a resume while an agent and a user interact. This research is a prototype for automatically generating dialogue questions without preparing a dialogue pattern in advance. The agent prepares the questions for a job

Using role play for collecting question-answer pairs for dialogue agents.
R Higashinaka, K Dohsaka, H Isozaki – INTERSPEECH, 2013 – isca-speech.org
Abstract Chatbot-like dialogue agents typically use character-anchored question-answer pairs for response generation. However, creating such pairs requires manual effort and is very costly. We propose using role play to efficiently collect such characteranchored

Building a Conversational Agent Overnight with Dialogue Self-Play
P Shah, D Hakkani-Tür, G Tür, A Rastogi… – arXiv preprint arXiv …, 2018 – arxiv.org
Abstract: We propose Machines Talking To Machines (M2M), a framework combining automation and crowdsourcing to rapidly bootstrap end-to-end dialogue agents for goal-oriented dialogues in arbitrary domains. M2M scales to new tasks with just a task schema

Strategies and mechanisms to enable dialogue agents to respond appropriately to indirect speech acts
G Briggs, M Scheutz – … (RO-MAN), 2017 26th IEEE International …, 2017 – ieeexplore.ieee.org
Humans often use indirect speech acts (ISAs) when issuing directives. Much of the work in handling ISAs in computational dialogue architectures has focused on correctly identifying and handling the underlying non-literal meaning. There has been less attention devoted to

Supporting Elementary School Computer Science Learning with Interactive Spoken Dialogue Agents
J Tsan – Proceedings of the eleventh annual International …, 2015 – dl.acm.org
Abstract To meet the demand for young students learning computer science, computer science curricula for students in elementary school (ages 5-11) are emerging. With those curricula comes the question, how do we gauge young students’ computer science

Humanlike dialogue agents
IA Chimir – ??????????? ?? ????’?????? ???????????. ??? …, 2014 – irbis-nbuv.gov.ua
The paper deals with an investigation and modeling of the inner mechanisms of human-human dialogue, with the final goal to construct an artificial humanlike dialogue agent. An ontological basis of human dialogue interaction, underlying follow-up reasoning, is obtained

Assigning a personality to a spoken dialogue agent through self-disclosure of behavior
Y Ogawa, K Miyazawa, H Kikuchi – … conference on Human-agent …, 2014 – dl.acm.org
Abstract In this study, we propose a method to assign a personality to a spoken dialogue agent and evaluate effectiveness of the method. Recently, some research studies on human-agent interaction (HAI) showed that it is possible to assign a personality by controlling non-

Building Effective Goal-Oriented Dialogue Agents
D Chen – pdfs.semanticscholar.org
Abstract Recent progress has seen an explosion in dialog systems, including voice-activated bots, text-based chatbots, and email-based bots for scheduling meetings. However real life interaction with these so-called intelligent agents consistently fall short of

Reinforcement learning for trading dialogue agents in non-cooperative negotiations
I Efstathiou – 2016 – ros.hw.ac.uk
Recent advances in automating Dialogue Management have been mainly made in cooperative environments-where the dialogue system tries to help a human to meet their goals. In non-cooperative environments though, such as competitive trading, there is still

From Eliza to Eugene: Approaching Fifty Years of Dialogue Agents
H Shah – researchgate.net
Page 1. AINL 2013, ST Petersburg, 17-18 May: http://ainlconf.ru/node/speakers From Eliza to Eugene: Approaching Fifty Years of Dialogue Agents Huma Shah School of Systems Engineering, Reading University, UK Abstract Do modern dialogue agents implement the same old strategy

Configuration of dialogue agent with multiple knowledge sources
R Jiang, RE Banchs, S Kim, LF D’Haro… – … Annual Summit and …, 2015 – ieeexplore.ieee.org
Knowledge base is a key component of a dialogue agent which determines its usability, performance as well as intelligence. Usually one type of knowledge source is tailored towards specific application or task. One challenge for developing multiple-domain dialogue

A Study on Dialogue Agent Adapting to Various Situations
A Jordan – 2016 – eprints.lib.hokudai.ac.jp
In the present world, machines and computers are used everywhere all days long by many different users. Therefore, many different kinds of interface have been set up in order to communicate with machines, such as for example buttons, mouse, touchscreen or keyboard.

Chinese-English SMT for cross-language dialogue agent support
X Duan, M Zhang – Signal and Information Processing …, 2014 – ieeexplore.ieee.org
Advances in Statistical Machine Translation (SMT) for breaking language barrier have been seen in recent years, and there is huge demand on cross-language dialog communication between people. In this paper we propose to leverage SMT for supporting cross-language

Spoken Dialog Agent Applications using Emotional Expressions
K Sumi – Emotions, Technology, and Design, 2016 – Elsevier
Abstract An increasing number of people are in need of mental care, because associated social issues include problems of bullying in schools, mental disability and hikikomori (a Japanese term to refer to the phenomenon of reclusive adolescents or young adults who

Personalizing Dialogue Agents: I have a dog, do you have pets too?
S Zhang, E Dinan, J Urbanek, A Szlam, D Kiela… – arXiv preprint arXiv …, 2018 – arxiv.org
Abstract: Chit-chat models are known to have several problems: they lack specificity, do not display a consistent personality and are often not very captivating. In this work we present the task of making chit-chat more engaging by conditioning on profile information. We collect

Assigning a Personality to a Spoken Dialogue Agent by Behavior Reporting
Y Ogawa, H Kikuchi – New Generation Computing, 2017 – Springer
Abstract A method to assign a personality to a spoken dialogue agent is proposed and evaluated. The proposed method assigns a personality using agent reporting about behavior independent of interaction with a user. The proposed method attempts to assigning

Statistical Response Method and Learning Data Acquisition using Gamified Crowdsourcing for a Non-task-oriented Dialogue Agent
Y Enokibori, K Takahashi, K Mase – Agents and Artificial Intelligence: 6th …, 2015 – Springer
Abstract. This paper presents a proposal of a construction method for non-task-oriented dialogue agents (chatbots) that are based on the statistical response method. The method prepares candidate utterances in advance. From the data, it learns which utterances are

Learning how to learn: an adaptive dialogue agent for incrementally learning visually grounded word meanings
Y Yu, A Eshghi, O Lemon – arXiv preprint arXiv:1709.10423, 2017 – arxiv.org
Abstract: We present an optimised multi-modal dialogue agent for interactive learning of visually grounded word meanings from a human tutor, trained on real human-human tutoring data. Within a life-long interactive learning period, the agent, trained using

Learning and Reusing Dialog for Repeated Interactions with a Situated Social Agent
J Kennedy, I Leite, A Pereira, M Sun, B Li… – … Intelligent Virtual Agents, 2017 – Springer
Abstract Content authoring for conversations is a limiting factor in creating verbal interactions with intelligent virtual agents. Building on techniques utilizing semi-situated learning in an incremental crowdworking pipeline, this paper introduces an embodied agent

Modeling Emotion And Motivation Based Agent For Tutorial Dialogue System
M Asam, SA Raza – sci-int.com
Abstract-It’sa challenging task to develop socially interactive agents, because the paradigm has shifted from behavioral to emotion and motivational based agents. The systems that claim to have the ability of natural language processing have some limitations in them. In

Characterizing and Modeling Linguistic Style in Dialogue for Intelligent Social Agents
S Oraby – Proceedings of the 22nd International Conference on …, 2017 – dl.acm.org
Abstract With increasing interest in the development of intelligent agents capable of learning, proficiently automating tasks, and gaining world knowledge, the importance of integrating the ability to converse naturally with users is more crucial now than ever before.

Exploring the Difference of the Impression on Human and Agent Listeners in Active Listening Dialog
HH Huang, N Konishi, S Shibusawa… – … Intelligent Virtual Agents, 2014 – Springer
Abstract Active listening is a communication technique that the listener listens to the speaker carefully and attentively by confirming or asking for more details aboutwhat they heard. In order to improve the effect, always-available and trustable conversational partners in

Participatory agent-based simulation to foster dialogue and build trust between local communities and researchers: a case study on bushmeat hunting in the periphery …
C Le Page, S Bobo Kadiri, K Towa, O William… – 2015 – agritrop.cirad.fr
To investigate the sustainability of bushmeat hunting activities in the region of the Korup National Park (South-West Cameroon), an agent-based model (ABM) representing snare trapping of blue duikers (Cephalophus monticola) was co-designed and used with local

Smart (but Also) Challenging Learning Environments: The Case of Conversational Agents That Foster Productive Peer Dialogue
SN Demetriadis, SD Tegos – … of Theory, Research, Practice, and Policy, 2016 – Springer
Abstract Smart learning environments (SLEs) are typically described as environments that offer rich learning interactions by making use of digital, context-aware, and adaptive technologies. This work introduces the concept of “smart challenging learning

Agent dialogue strategy based on priority of goals
A Beigi, N Mozayani – Telecommunications (IST), 2014 7th …, 2014 – ieeexplore.ieee.org
In multi agent systems, agents interact with each other through a dialogue protocol to inform each other the relevant facts in order to reach the common goals. In a dialogue the protocol defines the possible replies for a presented speech act and the strategy specifies which

Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning
L Chen, X Zhou, C Chang, R Yang, K Yu – Proceedings of the 2017 …, 2017 – aclweb.org
Abstract Hand-crafted rules and reinforcement learning (RL) are two popular choices to obtain dialogue policy. The rule-based policy is often reliable within predefined scope but not self-adaptable, whereas RL is evolvable with data but often suffers from a bad initial

Feedback of Interface Agents on Student Perception: Level, Dialogue, and Emotion
ZH Chen, CY Chou, SF Tseng, YC Su – Journal of Educational Technology & …, 2018 – JSTOR
ABSTRACT Although feedback from interface agents has recently attracted increasing research attention, most studies emphasize the cognitive influences. Thus, the effect of each feedback type on student perception remains unclear. This study focuses on three types of

A Taxonomy for Improving Dialog between Autonomous Agent Developers and Human-Machine Interface Designers
DJ Hooper, JP Duffy, GL Calhoun… – 2015 AAAI Fall Symposium …, 2015 – aaai.org
Abstract Autonomous agents require interfaces to define their interactions with humans. The coupling between agents and humans is often limited, with disjoint goals between the agent interface and its associated autonomous components. This leads to a gap in human

Modeling situation-dependent nonverbal expressions for a pair of embodied agent in a dialogue based on conversations in TV programs
K Okuuchi, K Kakusho, T Kojima… – … Conference on Human …, 2013 – Springer
Abstract Mathematical model for controlling nonverbal expressions of a pair of embodied agents designed for presenting various information through their dialogue is discussed. Nonverbal expressions of a human during conversation with others depend on those of

São Paulo Design Visions: Strategic design as an agent of dialog and transformation, 2007 São Paulo Design Visions: design estratégico como um agente de …
A Rossi Filho, AEE Stevaux, A Meroni, C Monti… – Cep – academia.edu
Este ensaio visa relatar o desenvolvimento de um projecto de investigação do SENAC São Paulo. A partir da valorização das ações e projectos já promovidos pelo parceiro brasileiro, o projeto promovido pelo Sistema de Design do Politécnico de Milão esboça um papel e

Occupation as an agent of social transformation and intercultural dialogue
N Pollard – academia.edu
Page 1. Occupation as an agent of social transformation and intercultural dialogue: the historical concept of occupation, Gramsci, oral culture and lore. Nick Pollard N.Pollard@shu.ac.uk Page 2. Aim … These experiences are the basis of our questioning of the status quo, of the direction of

Effect of sympathetic relation and unsympathetic relation in multi-agent spoken dialogue system
Y Shibahara, K Yamamoto… – … : Concepts, Theory And …, 2016 – ieeexplore.ieee.org
Recently, spoken dialog systems using speech recognition technology have been becoming popular. Such as chat-like dialog systems, these systems which do not have any specific purpose are called “Non-Task-oriented spoken dialog system”. In this study, we focused on

Data for Multi-agent learning in multi-domain spoken dialogue systems
M Gasic – 2015 – repository.cam.ac.uk
This dataset correspond to the results presented in NIPS 2015 Workshop on Spoken Language Understanding and Interaction, paper MULTI-AGENT LEARNING IN MULTI-DOMAIN SPOKEN DIALOGUE SYSTEMS and relates to Fig. 1 Two contrasts were

Conversational Agents as Learning Facilitators: Experiences With a Mobile Multimodal Dialogue System Architecture
D Griol, Z Callejas – Formative Assessment, Learning Data Analytics and …, 2016 – Elsevier
Abstract In this chapter, we discuss the wide variety of applications for which multimodal conversational systems are being used in education within the context of gamification. The chapter also describes a modular and scalable framework to develop such systems

Dialogue Act Recognition for Conversational Agents
LE Hacquebord – 2017 – dspace.library.uu.nl
The recognition of dialogue acts, actions that are performed through speech, is important for conversational agents to function well. Unfortunately, the studies that have been done on this topic vary a lot in methodology, so they are difficult to compare. Additionally, their results

Context respectful counseling agent integrated with robot nodding for dialog promotion
K Kurashige, S Tsuruta, E Sakurai… – Systems, Man, and …, 2017 – ieeexplore.ieee.org
Nowadays, a lot of IT personnel have psychological distress. Meanwhile, counselors to help them are lack in number. To solve the problem, we proposed a counseling agent (CA) called CRECA (context respectful counseling agent). CRECA listens to clients and promotes their

Agency via dialogue: a pragmatic, dialogue-based approach to agents
SR Dias – 2016 – repositorio.pucrs.br
This work addresses human communicative agency. The competence to instantiate a set of communicative procedures is taken as a component of human rationality that meets a key role of regulating our cognitive environment (a set of mental states, centrally assumptions

Agent Requirements for Effective and Efficient Task-Oriented Dialog
S Mohan, J Kirk, A Mininger, J Laird – 2015 AAAI Fall Symposium Series, 2015 – aaai.org
Abstract Dialog is a useful way for a robotic agent performing a task to communicate with a human collaborator, as it is a rich source of information for both the agent and the human. Such task-oriented dialog provides a medium for commanding, informing, teaching, and

Lifestyle Agent: The Chat-Oriented Dialogue System for Lifestyle Management
H Kawata, K Ookawara, M Muta, S Masuko… – International Conference …, 2017 – Springer
Abstract In this paper, we propose Lifestyle Agent, which manages user’s lifestyle in a chat format. Lifestyle agent counsels users through chat and encourages the formation of motivation with the aim of improving users’ lifestyle habits. In an evaluation experiment, we

Multi-Agent Dialogue Games and Dialogue Sequents for Proof Search and Scheduling.
M Sticht – CILC, 2016 – ceur-ws.org
Abstract. Dialogical games as introduced by Lorenzen and Lorenz describe a reasoning technique mainly used for intuitionistic and classical predicate logic: two players (proponent and opponent) argue about the validity of a given formula according to predefined rules. If

Perioperative dialogue on postoperative recovery measured by the use of pain medication, psychopharmaceutical agents and length of hospital stay
CL Swenne, L Hjelte, E Härdne… – Nordic Journal of …, 2018 – journals.sagepub.com
The effects of perioperative dialogue have been studied using qualitative methods, describing patient satisfaction with their care. However, they have not been studied in patients with peritoneal carcinomatosis who undergo major surgery, nor with quantitative

Multi-Agent Dialogue Games and Dialogue Sequents
M Sticht – PhDs in Logic VIII, 2015 – logic.at
… Distinguish between critical and non-critical attacks: • critical: ?? ?¬ non-critical: ?L ?R ?? ?? a? ? corresponds to ?r and ¬r rules of multi-conclusion sequent calculus. ? O’s concessions in a critical attack only committed if the corresp. P-agent defends (? promise). ? Structural rules

Intelligent Virtual Agents and Spoken Dialog Systems come together to Deliver Brief Health Interventions
U Yasavur, C Lisetti, N Rishe – cake.fiu.edu
Abstract We developed a virtual counseling system which can deliver brief alcohol health interventions via a 3D anthropomorphic speech-enabled interface-a new field for spoken dialog interactions with intelligent virtual agents in the health domain. We present our

Aspects of Protocol Conformance in Inter-agent Dialogue
N Maudet, F Sadri, F Toni – Citeseer
… 1. INTRODUCTION An agent communication protocol specifies the “rules of en- counter” [3] governing a dialogue between agents in a mul- tiagent system by determining which agent is allowed to say what in any given situation. It will usually allow for several alternative utterances

The church as a moral agent: In dialogue with Bram van de Beek
JM Vorster – HTS Teologiese Studies/Theological Studies, 2018 – hts.org.za
Abstract The latter part of the 20th century is known for a surge in the so-called ‘genitive theologies’. Usually, a genitive theology has an ulterior motive, aiming at the transformation of a society or the promotion of sound politics and economy. In recent years, this trend

Integrating User and Agent Models: A Deep Task-Oriented Dialogue System
W Wang, Y WU, Y Zhang, Z Lu, K Mo… – arXiv preprint arXiv …, 2017 – arxiv.org
Abstract: Task-oriented dialogue systems can efficiently serve a large number of customers and relieve people from tedious works. However, existing task-oriented dialogue systems depend on handcrafted actions and states or extra semantic labels, which sometimes

Dialogue enabling speech-to-text user assistive agent system for hearing-impaired person
S Lee, S Kang, DK Han, H Ko – Medical & biological engineering & …, 2016 – Springer
Abstract A novel approach for assisting bidirectional communication between people of normal hearing and hearing-impaired is presented. While the existing hearing-impaired assistive devices such as hearing aids and cochlear implants are vulnerable in extreme

Reprompts as error handling strategy in human-agent-dialog? User responses to a system’s display of non-understanding
C Opfermann, K Pitsch – Robot and Human Interactive …, 2017 – ieeexplore.ieee.org
In speech based technical systems, areprompt’can be deployed as a verbally non-explicit and semantically unspeciflc practice of making a failure-to-understand transparent. Users’ repeats or rephrasings of their previous answers might lead to further non-understandings,

Mathematics As An Agent Of Dialogue In The Society
JV Kureethara, M Joseph – Journal of Dharma: Dharmaram …, 2017 – researchgate.net
Abstract: Though Mathematics is mostly considered as a subject of the intelligent, it is used by everybody for daily activities. It acts as an efficient agent of dialogue in the society. Its role in transferring abstract knowledge to concrete experience, in interpreting the unknown and

Intercultural Dialogue in the Euro-Mediterranean Region: A Focus on Youths as Active Agents for Change
K Mamo – 2013 – digilib.gmu.edu
This thesis analysis focuses on the levels of interaction in the EuroMed region. Intercultural dialogue is the main frame of analysis and levels of interaction are translated from opinion poll surveys carried out in a 10 year time frame. Subsequently youths are individuated as the