@inproceedings{4f34b45ae2f1431aa85c8a80a848aaae,
title = "Query-biased summaries for tabular data",
abstract = "Government, research, and academic data portals publish a large amount of public data, but present tools make discovery difficult. In particular, search results do not support a user's decision whether or not to commit to a download of what might be a large data set. We describe a method for producing query-biased summaries of tabular data, which aims to support a user's download decision-or even to answer the question on the spot, with no further interaction. The method infers simple types in the data and query; automatically refines queries, where that makes sense; extracts relevant subsets of the complete table; and generates both graphical and tabular summaries of what remains. A small-scale user study suggests this both helps users identify useful results (fewer false negatives), and reduces wasted downloads (fewer false positives).",
keywords = "Data portals, Information retrieval, Tables",
author = "Vincent Au and Paul Thomas and Jayasinghe, {Gaya K.}",
note = "Publisher Copyright: {\textcopyright} 2016 ACM.; 21st Australasian Document Computing Symposium, ADCS 2016 ; Conference date: 06-12-2016 Through 07-12-2016",
year = "2016",
month = dec,
day = "5",
doi = "10.1145/3015022.3015027",
language = "English",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery (ACM)",
pages = "69--72",
editor = "Sarvnaz Karimi and Mark Carman",
booktitle = "ADCS 2016 - Proceedings of the 21st Australasian Document Computing Symposium",
address = "United States",
}