@unpublished{zamani2020mimics,
author = {Zamani, Hamed and Lueck, Gord and Chen, Everest and Quispe, Rodolfo and Luu, Flint and Craswell, Nick},
title = {MIMICS: A Large-Scale Data Collection for Search Clarification},
year = {2020},
month = {June},
abstract = {Search clarification has recently attracted much attention due to its applications in search engines. It has also been recognized as a major component in conversational information seeking systems. Despite its importance, the research community still feels the lack of a large-scale data for studying different aspects of search clarification. In this paper, we introduce MIMICS, a collection of search clarification datasets for real web search queries sampled from the Bing query logs. Each clarification in MIMICS is generated by a Bing production algorithm and consists of a clarifying question and up to five candidate answers. MIMICS contains three datasets: (1) MIMICS-Click includes over 400k unique queries, their associated clarification panes, and the corresponding aggregated user interaction signals (i.e., clicks). (2) MIMICS-ClickExplore is an exploration data that includes aggregated user interaction signals for over 60k unique queries, each with multiple clarification panes. (3) MIMICS-Manual includes over 2k unique real search queries. Each query-clarification pair in this dataset has been manually labeled by at least three trained annotators. It contains graded quality labels for the clarifying question, the candidate answer set, and the landing result page for each candidate answer.
MIMICS is publicly available for research purposes, thus enables researchers to study a number of tasks related to search clarification, including clarification generation and selection, user engagement prediction for clarification, click models for clarification, and analyzing user interactions with search clarification},
url = {http://approjects.co.za/?big=en-us/research/publication/mimics-a-large-scale-data-collection-for-search-clarification/},
}