Macaw: An Extensible Conversational Information Seeking Platform

TL;DR

Macaw is an open-source, modular platform designed to facilitate research in conversational information seeking by supporting multi-modal, multi-turn interactions and enabling both algorithmic and user-in-the-loop studies.

Contribution

The paper introduces Macaw, a flexible, extensible framework that supports diverse CIS tasks and research needs, filling a gap in tools for this emerging field.

Findings

Supports multi-turn, multi-modal interactions

Enables evaluation of new CIS algorithms

Facilitates user studies and data collection

Abstract

Conversational information seeking (CIS) has been recognized as a major emerging research area in information retrieval. Such research will require data and tools, to allow the implementation and study of conversational systems. This paper introduces Macaw, an open-source framework with a modular architecture for CIS research. Macaw supports multi-turn, multi-modal, and mixed-initiative interactions, and enables research for tasks such as document retrieval, question answering, recommendation, and structured data exploration. It has a modular design to encourage the study of new CIS algorithms, which can be evaluated in batch mode. It can also integrate with a user interface, which allows user studies and data collection in an interactive mode, where the back end can be fully algorithmic or a wizard of oz setup. Macaw is distributed under the MIT License.