AISEMay 1, 2017

MACA: A Modular Architecture for Conversational Agents

arXiv:1705.00673v220 citations
AI Analysis

This work addresses the problem of building conversational agents for researchers and developers by providing a flexible framework, though it is incremental as it builds on existing strategies.

The authors tackled the challenge of implementing dialogue systems by proposing MACA, a modular architecture that eases development and enables quick prototyping, facilitating technique development and reproduction of previous work.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes