TY  - CONF
ID  - SisLab1886
UR  - http://doi.org/10.1109/RIVF.2013.6719875
A1  - Le, Hong Phuong
A1  - Phan, Xuan Hieu
A1  - Tran, The Trung
Y1  - 2013/11//
N2  - This paper investigates the effect of the label bias problem of maximum entropy Markov models for part-of-speech tagging, a typical sequence prediction task in natural language processing. This problem has been underexploited and underappreciated. The investigation reveals useful information about the entropy of local transition probability distributions of the tagging model which enables us to exploit and quantify the label bias effect of part-of-speech tagging. Experiments on a Vietnamese treebank and on a French treebank show a significant effect of the label bias problem in both of the languages.
TI  - On the effect of the label bias problem in part-of-speech tagging
SP  - 103
M2  - Hanoi, Vietnam
AV  - none
EP  - 108
T2  - The 2013 IEEE RIVF International Conference on Computing and Communication Technologies, Research, Innovation, and Vision for the Future (RIVF)
ER  -