Information Extraction over Structured Data: Question Answering with Freebase

Abstract

Answering natural language questions using the Freebase knowledge base has recently been explored as a platform for advancing the state of the art in open domain semantic parsing. Those efforts map questions to sophisticated meaning representations that are then attempted to be matched against viable answer candidates in the knowledge base. Here we show that relatively modest information extraction techniques, when paired with a webscale corpus, can outperform these sophisticated approaches by roughly 34% relative gain.

View Slides

Extracted Key Phrases

6 Figures and Tables

020402014201520162017
Citations per Year

138 Citations

Semantic Scholar estimates that this publication has 138 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Yao2014InformationEO, title={Information Extraction over Structured Data: Question Answering with Freebase}, author={Xuchen Yao and Benjamin Van Durme}, booktitle={ACL}, year={2014} }