Difference between revisions of "DAO"
From Knoesis wiki
(Created page with "'''DAO''' is the acronym for '''D'''rug '''A'''buse '''O'''ntology.") |
|||
| Line 1: | Line 1: | ||
'''DAO''' is the acronym for '''D'''rug '''A'''buse '''O'''ntology. | '''DAO''' is the acronym for '''D'''rug '''A'''buse '''O'''ntology. | ||
| + | The PREDOSE research team has developed preliminary techniques that automatically extract semantic information from Web-based data. Such includes entities, generic sentiment expressions, relationships and triples. To perform entity identification, the research team relies on a combination of lexical and semantics-based techniques, based on a manually curated Drug Abuse Ontology (DAO) - pronounced dow), which is the first ontology for prescription drug abuse. To extract relationships the PREDOSE team has implemented a lexical and semantics-based technique applies a semantic similarity measure between relationship candidates, WordNet Synsets and predicates from the UMLS. For triple extraction the team has implemented a top-down pattern-based approach using DAO patterns, and the SystemT framework to extract triple patterns from text. | ||
Revision as of 16:00, 24 July 2017
DAO is the acronym for Drug Abuse Ontology.
The PREDOSE research team has developed preliminary techniques that automatically extract semantic information from Web-based data. Such includes entities, generic sentiment expressions, relationships and triples. To perform entity identification, the research team relies on a combination of lexical and semantics-based techniques, based on a manually curated Drug Abuse Ontology (DAO) - pronounced dow), which is the first ontology for prescription drug abuse. To extract relationships the PREDOSE team has implemented a lexical and semantics-based technique applies a semantic similarity measure between relationship candidates, WordNet Synsets and predicates from the UMLS. For triple extraction the team has implemented a top-down pattern-based approach using DAO patterns, and the SystemT framework to extract triple patterns from text.
