Ranking Triples using Entity Links in a Large Web Crawl - The Chicory Triple Scorer at WSDM Cup 2017
Information Retrieval
2017-12-25 v1
Abstract
This paper describes the participation of team Chicory in the Triple Ranking Challenge of the WSDM Cup 2017. Our approach deploys a large collection of entity tagged web data to estimate the correctness of the relevance relation expressed by the triples, in combination with a baseline approach using Wikipedia abstracts following [1]. Relevance estimations are drawn from ClueWeb12 annotated by Google's entity linker, available publicly as the FACC1 dataset. Our implementation is automatically generated from a so-called 'search strategy' that specifies declaratively how the input data are combined into a final ranking of triples.
Cite
@article{arxiv.1712.08355,
title = {Ranking Triples using Entity Links in a Large Web Crawl - The Chicory Triple Scorer at WSDM Cup 2017},
author = {Frank Dorssers and Arjen P. de Vries and Wouter Alink and Roberto Cornacchia},
journal= {arXiv preprint arXiv:1712.08355},
year = {2017}
}
Comments
Triple Scorer at WSDM Cup 2017, see arXiv:1712.08081