110 likes | 239 Views
Knowledge-rich Word Sense Disambiguation Rivaling Supervised Systems . Presenter : Cheng- Hui Chen Authors : Simone Paolo Ponzetto , Roberto Navigli ACL, 2010. Outlines. Motivation Objectives Methodology Experiments Conclusions Comments. WordNet. Motivation. Knowledge. Google.
E N D
Knowledge-rich Word Sense Disambiguation Rivaling Supervised Systems Presenter : Cheng-Hui ChenAuthors : Simone Paolo Ponzetto, Roberto NavigliACL, 2010
Outlines • Motivation • Objectives • Methodology • Experiments • Conclusions • Comments
WordNet Motivation • Knowledge • Google • Wiki • One of the main obstacles to high-performance WSD is the knowledge acquisition bottleneck. ? • Other source WSD algorithm
Objectives • To propose to automatically extend WordNet with large amounts of semantic relations from an encyclopedic resource, name Wikipedia. Knowledge WordNet Resource Wiki Resource WSD algorithm
Framework WordNet resource 1.Synonymy 2.Hypernymy/Hyponymy 3.Sisterhood 4.Gloss Wiki resource 1.Sense labels 2.Links 3.Categories
Methodology • Wiki • Sense labels • Links • Categories • WordNet • Synonymy • Hypernymy/Hyponymy • Sisterhood • Gloss
Mapping algorithm • SODA (WordNet) • 1. namely the sodium carbonate • Salt, acetate,sodium, chlorate, benzoate • 2.the drink • Drink, soft, cola, bitter • Drink (Wiki) • Soft, drink, cola, sugar 1. 2. 0 2 9 9
Experiments • Evaluation of the Mapping
Experiments ExtLesk: I am super man Gloss, Sisterhood, Synonymy, Hypernumy/Hyponymy • Coarse-grained WSD
Conclusions • This paper has presented a large-scale method for the automatic enrichment of a computational lexicon with encyclopedic relational knowledge. • The method enables simple knowledge-based WSD systems to perform as well as the highest-performing supervised system.
Comments • Advantages • This paper uses the consistent example. • Applications • Knowledge-based WSD system.