We propose a software architecture designed to ease the implementation of dialogue systems. The Modular Architecture for Conversational Agents (MACA) uses a plug-n-play style that allows quick prototyping, thereby facilitating the development of new techniques and the reproduction of previous work. The architecture separates the domain of the conversation from the agent's dialogue strategy, and as such can be easily extended to multiple domains. MACA provides tools to host dialogue agents on Amazon Mechanical Turk (mTurk) for data collection and allows processing of other sources of training data. The current version of the framework already incorporates several domains and existing dialogue strategies from the recent literature.
@article{arxiv.1705.00673,
title = {MACA: A Modular Architecture for Conversational Agents},
author = {Hoai Phuoc Truong and Prasanna Parthasarathi and Joelle Pineau},
journal= {arXiv preprint arXiv:1705.00673},
year = {2017}
}
Comments
The architecture needs to be tested further. Sorry for the inconvenience. We should be putting up the paper up soon