A Probabilistic Approach for Integrating Heterogeneous Knowledge Sources

Abstract

Abstract. Open Information Extraction (OIE) systems like Nell andReVerb have achieved impressive results by harvesting massive amounts of machine-readable knowledge with minimal supervision. However, the knowledge bases they produce still lack a clean, explicit semantic data model. This, on the other hand, could be provided by full-fledged semantic networks like DBpedia or Yago, which, in turn, could benefit from the additional coverage provided by Web-scale IE. In this paper, we bring these two strains of research together, and present a method to align terms from Nell with instances in DBpedia. Our approach is unsupervised in nature and relies on two key components. First, we automatically acquire probabilistic type information for Nell terms given a set of matching hypotheses. Second, we view the mapping task as the statistical inference problem of finding the most likely coherent mapping -i.e., the maximum a posteriori (MAP) mapping -based on the outcome of the first component used as soft constraint. These two steps are highly intertwined: accordingly, we propose an approach that iteratively refines type acquisition based on the output of the mapping generator, and vice versa. Experimental results on gold-standard data indicate that our approach outperforms a strong baseline, and is able to produce everimproving mappings consistently across iterations.

Improving Neural Knowledge Base Completion with Cross-Lingual Projections

“…A slight modification is the approach by (West et al, 2014) where lexicalized KB relations are posed as queries to a search engine and results are parsed to find pairs of entities between which the initially queried relation holds. Complementary to this, open information extraction methods (Etzioni et al, 2011;Faruqui and Kumar, 2015) extract large amounts of facts from text that can then be used for extending KBs (Dutta et al, 2014).…”

Enriching and improving the quality of linked data with GIS

“…This method uses Markov Logic Networks on the set of candidates retrieved from entities linked by properties confirming the matching hypothesis. The output can be improved iteratively by using dedicated "bootstrapping algorithm" [5]. A matching method described in this article follows the same general approach of combining spatial analysis with semantic and lexical analysis [17].…”

“…Data originating from the latter two sources are more exposed to errors [5]. In general, semi-structured and unstructured data sets are more likely to be noisy and incomplete [14].…”

“…The growth of data published on the Web in RDF as well as in dictionaries and ontologies has been dynamic and uncontrolled. Some of linked data comes from unstructured sources like free text or semi-structured sources like Wikipedia, which causes the data to be more prone to errors [5].…”

The ContrastMedium Algorithm: Taxonomy Induction From Noisy Knowledge Graphs With Just A Few Links

“…However, the output of these systems does not consist of a clean, fully-semantified output. Such output, on the other hand, could be provided by the vocabulary of large-scale ontologies like DBpedia (Bizer et al, 2009) or YAGO (Hoffart et al, 2013) and the integration of open and closed information extraction approaches (Dutta et al, 2014). The use of an encyclopedia-centric (e.g., Wikipedia-based) dictionary of entities leads to poor coverage of domain-specific terminologies .…”