{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/maca-a-modular-architecture-for","title":"MACA: A Modular Architecture for Conversational Agents","arxiv_id":"1705.00673","date":"2017-05-01","proceeding":"WS 2017 8","authors":["Hoai Phuoc Truong","Prasanna Parthasarathi","Joelle Pineau"],"abstract":"We propose a software architecture designed to ease the implementation of\ndialogue systems. The Modular Architecture for Conversational Agents (MACA)\nuses a plug-n-play style that allows quick prototyping, thereby facilitating\nthe development of new techniques and the reproduction of previous work. The\narchitecture separates the domain of the conversation from the agent's dialogue\nstrategy, and as such can be easily extended to multiple domains. MACA provides\ntools to host dialogue agents on Amazon Mechanical Turk (mTurk) for data\ncollection and allows processing of other sources of training data. The current\nversion of the framework already incorporates several domains and existing\ndialogue strategies from the recent literature.","url_abs":"http://arxiv.org/abs/1705.00673v2","url_pdf":"http://arxiv.org/pdf/1705.00673v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"maca-a-modular-architecture-for","repo_url":"https://github.com/ppartha03/MACA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}