Uncovering the Semantics of Wikipedia Pagelinks

Presutti, Valentina; Consoli, Sergio; Nuzzolese, Andrea Giovanni; Recupero, Diego Reforgiato; Gangemi, Aldo; Bannour, Ines; Zargayouna, Haïfa

doi:10.1007/978-3-319-13704-9_32

Cited by 24 publications

(25 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the sake of completeness, these results are summarised in Section 5.2 (for additional details, the reader can refer to [38]). With the help of crowdsourcing an additional, more extensive evaluation of the current implementation of Legalo was performed, which allowed us to better assess its performances and open issues.…”

Section: Results and Evaluationmentioning

confidence: 99%

“…Additionally, the paper includes a brief description of a specific implementation of OKE, specialised for extracting the semantics of Wikipedia pagelinks, which has been evaluated in [38] showing promising results.…”

Section: Contributionmentioning

confidence: 99%

“…A specialised version of Legalo for typing Wikipedia pagelinks (Legalo-Wikipedia) 27 was presented in [38], however it relied on a previous version of the tool. In fact, Legalo-Wikipedia depends on Legalo, hence it evolves with it, and specialises it with two additional features: (i) a sentence extractor specialised for Wikipedia HTML formatting, and (ii) a subject resolver specialised for Wikipedia.…”

Section: Legalo Pipeline and Componentsmentioning

confidence: 99%

“…In fact, Legalo-Wikipedia depends on Legalo, hence it evolves with it, and specialises it with two additional features: (i) a sentence extractor specialised for Wikipedia HTML formatting, and (ii) a subject resolver specialised for Wikipedia. A detailed description of this implementation can be found in [38].…”

Section: Legalo Pipeline and Componentsmentioning

confidence: 99%

“…Each snippet is then passed to Legalo as input for generating the Semantic Web property. The version of legalo-wikipedia presented in [38] relied on a previous version of Legalo, which supported less general generative rules and did not perform the relevant relation assessment or the formalisation of the generated property.…”

Section: Legalo Pipeline and Componentsmentioning

confidence: 99%

See 4 more Smart Citations

From hyperlinks to Semantic Web properties using Open Knowledge Extraction

Presutti

Nuzzolese

Consoli

et al. 2016

Self Cite

View full text Add to dashboard Cite

Abstract. Open information extraction approaches are useful but insufficient alone for populating the Web with machine readable information as their results are not directly linkable to, and immediately reusable from, other Linked Data sources. This work proposes a novel paradigm, named Open Knowledge Extraction, and its implementation (Legalo) that performs unsupervised, open domain, and abstractive knowledge extraction from text for producing directly usable machine readable information. The implemented method is based on the hypothesis that hyperlinks (either created by humans or knowledge extraction tools) provide a pragmatic trace of semantic relations between two entities, and that such semantic relations, their subjects and objects, can be revealed by processing their linguistic traces (i.e. the sentences that embed the hyperlinks) and formalised as Semantic Web triples and ontology axioms. Experimental evaluations conducted on validated text extracted from Wikipedia pages, with the help of crowdsourcing, confirm this hypothesis showing high performances. A demo is available at http://wit.istc.cnr.it/ stlab-tools/legalo.

show abstract

Section: Results and Evaluationmentioning

confidence: 99%

Section: Contributionmentioning

confidence: 99%