Fine-Grained Geographical Relation Extraction from Wikipedia

From Wikipedia Quality
Revision as of 00:49, 17 May 2019 by Agnieszka (talk | contribs) (Created page with "{{Infobox work | title = Fine-Grained Geographical Relation Extraction from Wikipedia | date = 2010 | authors = André Blessing<br />Hinrich Schütze | link = http://w...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search


Fine-Grained Geographical Relation Extraction from Wikipedia
Authors
André Blessing
Hinrich Schütze
Publication date
2010
Links
Original

Fine-Grained Geographical Relation Extraction from Wikipedia - scientific work related to Wikipedia quality published in 2010, written by André Blessing and Hinrich Schütze.

Overview

In this paper, authors present work on enhancing the basic data resource of a context-aware system. First, authors introduce a supervised approach to extracting geographical relations on a fine-grained level. Second, authors present a novel way of using Wikipedia as a corpus based on self-annotation. A self-annotation is an automatically created high-quality annotation that can be used for training and evaluation. The fined-grained relations are used to complete gazetteer data. The precision and recall scores of more than 97% confirm that a statistical IE pipeline can be used to improve the data quality of community-based resources.

Embed

Wikipedia Quality

André, Blessing; Hinrich, Schütze. (2010). "[[Fine-Grained Geographical Relation Extraction from Wikipedia]]".

English Wikipedia

{{cite journal |last1=André |first1=Blessing |last2=Hinrich |first2=Schütze |title=Fine-Grained Geographical Relation Extraction from Wikipedia |date=2010 |url=https://wikipediaquality.com/wiki/Fine-Grained_Geographical_Relation_Extraction_from_Wikipedia}}

HTML

André, Blessing; Hinrich, Schütze. (2010). &quot;<a href="https://wikipediaquality.com/wiki/Fine-Grained_Geographical_Relation_Extraction_from_Wikipedia">Fine-Grained Geographical Relation Extraction from Wikipedia</a>&quot;.