A Distant Learning Approach for Extracting Hypernym Relations from Wikipedia Disambiguation Pages

Kamel, Mouna; Santos, Cássia Trojahn dos; Ghamnia, Adel; Aussenac-Gilles, Nathalie; Fabre, Cécile

doi:10.1016/j.procs.2017.08.208

Cited by 36 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This involves automatically extracting relations from text for building, enriching or populating them. This task usually relies on general purpose corpora as Wikipedia or WordNet and on knowledge extractors mainly exploiting their specific structural elements [22] or sub-corpora [15]. Several of these extractors have targeted these structures in order to enrich or to populate resources as DBpedia [2], YAGO or BabelNet [23].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Towards Enriching DBpedia from Vertical Enumerative Structures Using a Distant Learning Approach

Kamel

Santos

2018

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Automatic construction of semantic resources at large scale usually relies on general purpose corpora as Wikipedia. This resource, by nature rich in encyclopedic knowledge, exposes part of this knowledge with strongly structured elements (infoboxes, categories, etc.). Several extractors have targeted these structures in order to enrich or to populate semantic resources as DBpedia, YAGO or BabelNet. The remain semistructured textual structures, such as vertical enumerative structures (those using typographic and dispositional layout) have been however under-exploited. However, frequent in corpora, they are rich sources of specific semantic relations, such as hypernyms. This paper presents a distant learning approach for extracting hypernym relations from vertical enumerative structures of Wikipedia, with the aim of enriching DBpedia. Our relation extraction approach achieves an overall precision of 62%, and 99% of the extracted relations can enrich DBpedia, with respect to a reference corpus.

show abstract

Section: Introductionmentioning

confidence: 99%

“…We focus on French because semantic resources targeting this language are scarce. We have already proposed a distant supervised approach and implemented a tool for identifying hypernym relations from disambiguation Wikipedia pages [15]. We propose to adapt this approach in this new context, i.e.…”

Section: Introductionmentioning

confidence: 99%