Word Sense Disambiguation On Semeval 2013

Results

Performance results of various models on this benchmark

		Paper Title
SemCor+WNGC, hypernyms	78.7	Sense Vocabulary Compression through the Semantic Knowledge of WordNet for Neural Word Sense Disambiguation
SemCor+WNGT, vocabulary reduced, ensemble	72.63	Improving the Coverage and the Generalization Ability of Neural Word Sense Disambiguation through Hypernymy and Hyponymy Relationships
LSTMLP (T:SemCor, U:1K)	69.5	Semi-supervised Word Sense Disambiguation with Neural Models
LSTMLP (T:OMSTI, U:1K)	68.1	Semi-supervised Word Sense Disambiguation with Neural Models
LSTMLP (T:SemCor, U:OMSTI)	67.9	Semi-supervised Word Sense Disambiguation with Neural Models
LSTM (T:OMSTI)	67.3	Semi-supervised Word Sense Disambiguation with Neural Models
GASext (Concatenation)	67.2	Incorporating Glosses into Neural Word Sense Disambiguation
GASext (Linear)	67.1	Incorporating Glosses into Neural Word Sense Disambiguation
LSTM (T:SemCor)	67.0	Semi-supervised Word Sense Disambiguation with Neural Models
GAS (Concatenation)	67.0	Incorporating Glosses into Neural Word Sense Disambiguation
GAS (Linear)	66.7	Incorporating Glosses into Neural Word Sense Disambiguation
ShotgunWSD 2.0	63.05	ShotgunWSD: An unsupervised algorithm for global word sense disambiguation inspired by DNA sequencing

0 of 12 row(s) selected.