UNT-Yahoo: SuperSenseLearner: Combining SenseLearner with SuperSense and other Coarse Semantic Features

Description:

This paper discusses combining SenseLearner with SuperSence and other coarse semantic features.

Creator(s):
Creation Date: June 2007
Partner(s):
UNT College of Engineering
Collection(s):
UNT Scholarly Works
Usage:
Total Uses: 61
Past 30 days: 1
Yesterday: 0
Creator (Author):
Mihalcea, Rada, 1974-

University of North Texas

Creator (Author):
Csomai, Andras

University of North Texas

Creator (Author):
Ciaramita, Massimiliano

Yahoo! Research Barcelona

Publisher Info:
Place of Publication: [Stroudsburg, Pennsylvania]
Date(s):
  • Creation: June 2007
Description:

This paper discusses combining SenseLearner with SuperSence and other coarse semantic features.

Degree:
Note:

Abstract: We describe the SuperSenseLearner system that participated in the English all-words disambiguation task. The system relies on automatically-learned semantic models using collocational features coupled with features extracted from the annotations of coarse-grained semantic categories generated by an HMM tagger.

Physical Description:

4 p.

Language(s):
Subject(s):
Keyword(s): word sense disambiguation | SuperSenseLearner | semantic ambiguity | sense-annotated data sets
Source: Fourth International Workshop on the Semantic Evaluations, 2007, Prague, Czech Republic
Contributor(s):
Partner:
UNT College of Engineering
Collection:
UNT Scholarly Works
Identifier:
  • ARK: ark:/67531/metadc30998
Resource Type: Paper
Format: Text
Rights:
Access: Public