VNU-UET Repository

On the effect of the label bias problem in part-of-speech tagging

Le, Hong Phuong and Phan, Xuan Hieu and Tran, The Trung (2013) On the effect of the label bias problem in part-of-speech tagging. In: The 2013 IEEE RIVF International Conference on Computing and Communication Technologies, Research, Innovation, and Vision for the Future (RIVF), 10-13 November 2013, Hanoi, Vietnam.

Full text not available from this repository. (Request a copy)

Abstract

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.

Item Type: Conference or Workshop Item (Paper)
Subjects: Information Technology (IT)
Divisions: Faculty of Information Technology (FIT)
Depositing User: A/Prof. Xuan Hieu Phan
Date Deposited: 14 Nov 2016 02:37
Last Modified: 14 Nov 2016 02:37
URI: http://eprints.uet.vnu.edu.vn/eprints/id/eprint/1886

Actions (login required)

View Item View Item