Abstract
Hypernym extraction from Wikipédia The volume of available documents on the Web continues to increase, the texts contained in these documents are rich information describing concepts and relationships between concepts specific to a particular field. In this paper, we propose and exploit an hypernymy extractor based on lexico-syntactic patterns designed for Wikipedia semi-structured pages, especially the disambiguation pages, to enrich a knowledge base as BabelNet and DBPedia. The results show a precision of 0.68 and a recall of 0.75 for the patterns that we have defined, and an enrichment rate up to 33% for both BabelNet and DBPédia semantic resources.- Anthology ID:
- 2016.jeptalnrecital-recital.4
- Volume:
- Actes de la conférence conjointe JEP-TALN-RECITAL 2016. volume 3 : RECITAL
- Month:
- 7
- Year:
- 2016
- Address:
- Paris, France
- Editors:
- Laurence Danlos, Thierry Hamon
- Venue:
- JEP/TALN/RECITAL
- SIG:
- Publisher:
- AFCP - ATALA
- Note:
- Pages:
- 40–51
- Language:
- URL:
- https://aclanthology.org/2016.jeptalnrecital-recital.4
- DOI:
- Cite (ACL):
- Adel Ghamnia. 2016. Hypernym extraction from Wikipedia. In Actes de la conférence conjointe JEP-TALN-RECITAL 2016. volume 3 : RECITAL, pages 40–51, Paris, France. AFCP - ATALA.
- Cite (Informal):
- Hypernym extraction from Wikipedia (Ghamnia, JEP/TALN/RECITAL 2016)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2016.jeptalnrecital-recital.4.pdf