@inproceedings{5533b9ac484b4ed7915a19612088097e,
title = "Harvesting facts from textual web sources by constrained label propagation",
abstract = "There have been major advances on automatically constructing large knowledge bases by extracting relational facts from Web and text sources. However, the world is dynamic: periodic events like sports competitions need to be interpreted with their respective timepoints, and facts such as coaching a sports team, holding political or business positions, and even marriages do not hold forever and should be augmented by their respective timespans. This paper addresses the problem of automatically harvesting temporal facts with such extended time-awareness. We employ pattern-based gathering techniques for fact candidates and construct a weighted pattern-candidate graph. Our key contribution is a system called PRAVDA based on a new kind of label propagation algorithm with a judiciously designed loss function, which iteratively processes the graph to label good temporal facts for a given set of target relations. Our experiments with online news and Wikipedia articles demonstrate the accuracy of this method.",
keywords = "knowledge harvesting, label propagation, temporal facts",
author = "Yafang Wang and Bin Yang and Lizhen Qu and Marc Spaniol and Gerhard Weikum",
year = "2011",
doi = "10.1145/2063576.2063698",
language = "英语",
isbn = "9781450307178",
series = "International Conference on Information and Knowledge Management, Proceedings",
pages = "837--846",
booktitle = "CIKM'11 - Proceedings of the 2011 ACM International Conference on Information and Knowledge Management",
note = "20th ACM Conference on Information and Knowledge Management, CIKM'11 ; Conference date: 24-10-2011 Through 28-10-2011",
}