Webis Query-Task-Mapping Corpus 2019 (Webis-QTM-19)

<p>The Webis Query-Task-Mapping Corpus 2019 (Webis-QTM-19) comprises three benchmark datasets on the query-task-mapping problem, which consists of finding the correct task for a new query in a given task-split background query log.</p> <p>It comprises three subdatasets in separate CSV files, each of which has three columns:</p> <ul> <li>Query. The query string.</li> <li>Source. The source of the query. In all datasets, a source field with value&nbsp; &#39;google&#39; or &#39;bing&#39; indicates that the query was derived from query suggestions&nbsp; from the respective search engine; otherwise, the query is from one of the underlying base corpora: <ul> <li>&#39;lucc&#39; : lucchese:2011</li> <li>&#39;webis&#39; : stein:2013b</li> <li>&#39;trc&#39;&nbsp; : stein:2016a</li> <li>&#39;trec&#39;&nbsp; : various collections of TREC queries</li> <li>&#39;wikihow&#39; : based on titles of wikiHow questions</li> </ul> </li> <li>Task. The ID of the ground-truth task for the corresponding query.</li> </ul> <p><br> Further details can be found in reference:<br> Michael V&ouml;lske, Ehsan Fatehifar, Benno Stein, and Matthias Hagen. Query-Task Mapping. In 42nd International ACM Conference on Research and Development in Information Retrieval (SIGIR 2019), July 2019. ACM.<br> http://doi.acm.org/10.1145/3331184.3331286</p>