An Integrated Approach for Large-Scale Relation Extraction from the Web - Archive ouverte HAL Access content directly
Conference Papers Year : 2013

An Integrated Approach for Large-Scale Relation Extraction from the Web

Abstract

Deriving knowledge from information stored in unstructured documents is a major challenge. More specifically, binary relationships representing facts between entities can be extracted to populate semantic triple stores or large knowledge bases. The main constraint of all knowledge extraction approaches is to find a trade-off between quality and scalability. Thus, we propose in this paper SPIDER, a novel integrated system for extracting binary relationships at large scale. Through series of experiments, we show the benefit of our approach, which in general, outperforms existing systems both in terms of quality (precision and the number of discovered facts) and scalability.

Dates and versions

hal-01339299 , version 1 (29-06-2016)

Identifiers

Cite

Naimdjon Takhirov, Fabien Duchateau, Trond Aalberg, Solvberg Ingeborg. An Integrated Approach for Large-Scale Relation Extraction from the Web. Asia-Pacific Web Conference, Apr 2013, Sydney, Australia. pp.163-175, ⟨10.1007/978-3-642-37401-2_18⟩. ⟨hal-01339299⟩
68 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More