TY  - CONF
ID  - SisLab1885
UR  - http://doi.org/10.1007/978-3-319-11680-8_52
A1  - Le, Hong Phuong
A1  - Phan, Xuan Hieu
A1  - Nguyen, Tien Dung
Y1  - 2014/10//
N2  - Question classification is a first necessary task of automatic question
answering systems. Linguistic features play an important role in developing an accurate question classifier. This paper proposes to use typed dependencies which are extracted automatically from dependency parses of questions to improve accuracy of classification. Experiment results show that with only surface typed dependencies,
one can improve the accuracy of a discriminative question classifier by over 8.0% on two benchmark datasets.
VL  - 326
SN  - 2194-5357
TI  - Using Dependency Analysis to Improve Question Classification
SP  - 653
M2  - Hanoi, Vietnam
AV  - restricted
EP  - 665
T2  - The 8th International Conference on Knowledge and Systems Engineering (KSE)
ER  -