Macaw: An Extensible Conversational Information Seeking Platform

  title={Macaw: An Extensible Conversational Information Seeking Platform},
  author={Hamed Zamani and Nick Craswell},
  journal={Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval},
  • Hamed Zamani, Nick Craswell
  • Published 18 December 2019
  • Computer Science
  • Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval
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… 

Figures from this paper

Agent Dialogue: A Platform for Conversational Information Seeking Experimentation
The Agent Dialogue (AD) platform is presented, an open-source system developed for researchers to perform Wizard-of-Oz CIS experiments that includes support for centralized structure logging as well as offline relevance annotation.
Wizard of Search Engine: Access to Information Through Conversations with Search Engines
This work forms a pipeline for CIS with six subtasks: intent detection, keyphrase extraction, action prediction, query selection, passage selection, and response generation, and designs a neural architecture that can reduce the requirements of WISE in scale by making full use of available data.
Conversational Information Seeking: Theory and Application
This tutorial aims to be an introduction to CIS for newcomers to CIS in addition to the recent advanced topics and state-of-the-art approaches for students and researchers with moderate knowledge of the topic.
Towards Multi-Modal Conversational Information Seeking
This paper bridges the gap between the multi-modal and CIS research and provides a formal definition for MMCIS, and proposes and implements a practical open-source framework for facilitating MMC IS research.
Conversations with Search Engines: SERP-based Conversational Response Generation
In this article, we address the problem of answering complex information needs by conducting conversations with search engines, in the sense that users can express their queries in natural language
TaskMAD: A Platform for Multimodal Task-Centric Knowledge-Grounded Conversational Experimentation
This work introduces Task-oriented Multimodal Agent Dialogue (TaskMAD), a new platform that supports the creation of interactive multimodal and task-centric datasets in a Wizard-of-Oz experimental setup and supports a spectrum of tasks that span open-domain exploratory search to traditional frame-based dialogue tasks.
Chatty Goose: A Python Framework for Conversational Search
An overview of the Chatty Goose framework is provided and how to instantiate a new system from scratch is demonstrated, so that a comparable run can be reproduced with just a few lines of code.
Analysing Mixed Initiatives and Search Strategies during Conversational Search
A model for conversational search is presented from which it shows that query clarifications are better when asked first, while query suggestions are better after presenting results, and that the best strategy and approach depends on the trade-offs between the relative costs between querying and giving feedback.
How to Approach Ambiguous Queries in Conversational Search? A Survey of Techniques, Approaches, Tools and Challenges
This work provides a divine overview of characteristics of ambiguous queries and contributes to better understanding of the existing technologies and challenges in CSS focus on disambiguation of unclear queries from various dimensions.
Conversational Search - A Report from Dagstuhl Seminar 19461
The executive summary, overview of invited talks, and findings from the seven working groups which cover the definition, evaluation, modelling, explanation, scenarios, applications, and prototype of Conversational Search are provided.


MISC: A data set of information-seeking conversations
This work introduces the Microso‰ Information-Seeking Conversation data (MISC), a set of recordings of information-seeking conversations between human “seekers” and “intermediaries” that it hopes will support conversational retrieval interfaces both in engineering and evaluation.
Towards Conversational Search and Recommendation: System Ask, User Respond
This paper proposes a System Ask -- User Respond (SAUR) paradigm for conversational search, defines the major components of the paradigm, and designs a unified implementation of the framework for product search and recommendation in e-commerce.
A Theoretical Framework for Conversational Search
This paper studies conversational approaches to information retrieval, presenting a theory and model of information interaction in a chat setting, and shows that while theoretical, the model could be practically implemented to satisfy the desirable properties presented.
Asking Clarifying Questions in Open-Domain Information-Seeking Conversations
This paper formulate the task of asking clarifying questions in open-domain information-seeking conversational systems, propose an offline evaluation methodology for the task, and collect a dataset, called Qulac, through crowdsourcing, which significantly outperforms competitive baselines.
Vote Goat: Conversational Movie Recommendation
Vote Goat is introduced, a conversational recommendation agent built using Google's DialogFlow framework that uses gamification to incentivize movie voting interactions with the 'Greatest Of All Time' movies derived from user ratings.
CoQA: A Conversational Question Answering Challenge
CoQA is introduced, a novel dataset for building Conversational Question Answering systems and it is shown that conversational questions have challenging phenomena not present in existing reading comprehension datasets (e.g., coreference and pragmatic reasoning).
Conversational Recommender System
This work proposes to integrate research in dialog systems and recommender systems into a novel and unified deep reinforcement learning framework to build a personalized conversational recommendation agent that optimizes a per session based utility function.
Coached Conversational Preference Elicitation: A Case Study in Understanding Movie Preferences
A new approach to obtaining user preferences in dialogue: Coached Conversational Preference Elicitation that allows collection of natural yet structured conversational preferences.
Towards Deep Conversational Recommendations
This paper collects ReDial, a data set consisting of over 10,000 conversations centered around the theme of providing movie recommendations and uses this dataset to explore new neural architectures, mechanisms and methods suitable for composing conversational recommendation systems.
QuAC: Question Answering in Context
QuAC introduces challenges not found in existing machine comprehension datasets: its questions are often more open-ended, unanswerable, or only meaningful within the dialog context, as it shows in a detailed qualitative evaluation.