4.4 Article

An assertion and alignment correction framework for large scale knowledge bases

Journal

SEMANTIC WEB
Volume 14, Issue 1, Pages 29-53

Publisher

IOS PRESS
DOI: 10.3233/SW-210448

Keywords

Knowledge base; assertion correction; alignment correction; semantic embedding; constraints

Ask authors/readers for more resources

This study proposes a general correction framework to effectively correct erroneous assertions and alignments, achieving promising results through methods such as lexical matching, context-aware sub-KB extraction, semantic embedding, soft constraint mining, and semantic consistency checking.
Various knowledge bases (KBs) have been constructed via information extraction from encyclopedias, text and tables, as well as alignment of multiple sources. Their usefulness and usability is often limited by quality issues. One common issue is the presence of erroneous assertions and alignments, often caused by lexical or semantic confusion. We study the problem of correcting such assertions and alignments, and present a general correction framework which combines lexical matching, context-aware sub-KB extraction, semantic embedding, soft constraint mining and semantic consistency checking. The framework is evaluated with one set of literal assertions from DBpedia, one set of entity assertions from an enterprise medical KB, and one set of mapping assertions from a music KB constructed by integrating Wikidata, Discogs and MusicBrainz. It has achieved promising results, with a correction rate (i.e., the ratio of the target assertions/alignments that are corrected with right substitutes) of 70.1%, 60.9% and 71.8%, respectively.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.4
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available