Matching Domain and Top-level ontologies exploring Word Sense Disambiguation and Word Embedding - Archive ouverte HAL Access content directly
Book Sections Year : 2018

Matching Domain and Top-level ontologies exploring Word Sense Disambiguation and Word Embedding

(1) , (1) , (2, 3) , (1)
1
2
3

Abstract

Top-level ontologies play an important role in the construction and integration of domain ontologies, providing a well-founded reference model that can be shared across domains. While most efforts in ontology matching have been particularly dedicated to domain ontologies, the problem of matching domain and top-level ontologies has been addressed to a lesser extent. This is a challenging task in the field, specially due to the different levels of abstraction of these ontologies. This paper addresses this problem by proposing an approach that relies on existing alignments between WordNet and top-level ontologies. Our approach explores word sense disambiguation and word embedding models. We evaluate our approach in the task of matching DOLCE and SUMO top-level ontologies to ontologies from three different domains.
Not file

Dates and versions

hal-02982985 , version 1 (29-10-2020)

Identifiers

Cite

Daniela Schmidt, Rafael Basso, Cassia Trojahn dos Santos, Renata Vieira. Matching Domain and Top-level ontologies exploring Word Sense Disambiguation and Word Embedding. Demidova; Elena and Zaveri; Amrapali and Simperl; Elena. Emerging Topics in Semantic Technologies - ISWC 2018 Satellite Events [best papers from 13 of the workshops co-located with the ISWC 2018 conference], 36: Emerging Topics in Semantic Technologies, IOS Press, pp.27--38, 2018, http://ebooks.iospress.nl/bookseries/studies-on-the-semantic-web, ⟨10.3233/978-1-61499-894-5-27⟩. ⟨hal-02982985⟩
14 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More