Title of article
Hybrid learning of Syntactic and Semantic Dependencies
Author/Authors
Bor-Lin Yao، نويسنده , , Chengjie Sun، نويسنده , , Lu Li، نويسنده , , Zhixin Hao & Xiaolong Wang، نويسنده ,
Issue Information
روزنامه با شماره پیاپی سال 2010
Pages
13
From page
187
To page
199
Abstract
This paper presents our solution for jointly parsing of syntactic and semantic dependencies. The Maximum Entropy (ME) classifier is selected in this system. Also the Mutual Information (MI) model was utilized into feature selection of dependency labeling. Results show that the MI model allows the system to get better performance and reduce training hours.
Keywords
Maximum Entropy , Mutual information , Semantic Role Labeling (SRL) , Syntactic Parser
Journal title
Computer and Information Science
Serial Year
2010
Journal title
Computer and Information Science
Record number
678531
Link To Document