• Corpus ID: 243429

AIDA: Artificial Intelligent Dialogue Agent

  title={AIDA: Artificial Intelligent Dialogue Agent},
  author={Rafael E. Banchs and Ridong Jiang and Seokhwan Kim and Arthur Niswar and Kheng Hui Yeo},
  booktitle={SIGDIAL Conference},
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 interaction engines across multiple domains and communication styles such as command, question answering, task-oriented dialogue and chat-oriented dialogue. The platform accepts both speech and text as input modalities by either direct microphone/keyboard… 

Figures and Tables from this paper

Survey on Intelligent Dialogue in e-Learning Systems

An overview of automated dialogue characteristics and a survey on recent research efforts in academia and industry in building intelligent dialogue capable systems are provided.

Dialogue Management in Conversational Systems: A Review of Approaches, Challenges, and Opportunities

This article studies dialogue management from an in-depth design perspective, discusses the state-of-the-art approaches, identifies their recent advances and challenges, and provides an outlook on future research directions.

A Natural Language Approach to Human-Robot Interaction

With HRI experiencing a huge increase in interest over the last years, we have to think of ways how to improve our coexistence with robots. Since service robots are now applied in areas, where HRI

Chatbots for troubleshooting: A survey

Troubleshooting chatbots are chatbots that aim at automating troubleshooting contact centers and services and have inspired considerable interest in industry due to their cost savings potential.

Remembering a Conversation – A Conversational Memory Architecture for Embodied Conversational Agents

This work proposes, implements, and test a unified episodic memory architecture for ECAs, and describes a process that determines the prevalent contexts in the conversations obtained from the interactions, as well as demonstrating the use of multiple techniques to extract and store relevant snippets from long conversations.

Combining Open Domain Question Answering with a Task-Oriented Dialog System

It is shown that the modular dialog system framework is very suitable for this combination of conversational agents and that the performance of each agent decreases only marginally through the modular setting.

Reusable Abstractions and Patterns for Recognising Compositional Conversational Flows

This paper proposes three types of reusable patterns for recognising compositional conversationalows and therefore automatically support increased complexity and expressivity during the conversation.

Why Industrial Robots Should Become More Social - On the Design of a Natural Language Interface for an Interactive Robot Welder

It is argued that these robot capabilities can be highly beneficial in industrial environments, enhancing the human-robot communication and contributing to a shift in the interaction paradigm from industrial towards social.

eLmL 2019 Proceedings

An educational experience based on a technological development that is implemented on a smartphone using augmented reality is presented to facilitate learning by maintaining the attention and interest of users/learners through game techniques, and to develop soft skills, such as teamwork and lifelong learning.



Component Pluggable Dialogue Framework and Its Application to Social Robots

This paper designs and develops a component pluggable event-driven dialogue framework for service robots that works for all the robots that need speech interface, and improves the system robustness, reliability, and maintainability.

IRIS: a Chat-oriented Dialogue System based on the Vector Space Model

This system demonstration paper presents IRIS (Informal Response Interactive System), a chat-oriented dialogue system based on the vector space model framework. The system belongs to the class of

A Two-Stage Domain Selection Framework for Extensible Multi-Domain Spoken Dialogue Systems

A general and effective domain selection framework for multi-domain spoken dialogue systems that employ distributed domain experts that achieves both extensibility and robustness against speech recognition errors.

Multi-Domain Spoken Dialogue System with Extensibility and Robustness against Speech Recognition Errors

A multi-domain spoken dialogue system that can handle user requests across multiple domains and is equipped with a robust and extensible domain selection method that can prevent dialogues from continuously being stuck in an erroneous domain is developed.

A Two-Step Approach for Efficient Domain Selection in Multi-Domain Dialog Systems

  • Injae LeeSeokhwan Kim G. G. Lee
  • Computer Science
    Natural Interaction with Robots, Knowbots and Smartphones, Putting Spoken Dialog Systems into Practice
  • 2012
This paper discusses a domain selection method for multi-domain dialog systems to generate the most appropriate system utterance in response to a user utterance. We present a two-step approach for

Programmer Information