Vietnamese Named Entity Recognition using Token Regular Expressions and Bidirectional Inference

Abstract

This paper describes an efficient approach to improve the accuracy of a named entity recognition system for Vietnamese. The approach combines regular expressions over tokens and a bidirectional inference method in a sequence labelling model. The proposed method achieves an overall $F_1$ score of 89.66% on a test set of an evaluation campaign, organized in late 2016 by the Vietnamese Language and Speech Processing (VLSP) community.

Submitted to the VLSP Workshop 2016

Cited by in corpus (5)

• Improving Sequence Tagging for Vietnamese Text Using Transformer-based Neural Models
• End-to-end Recurrent Neural Network Models for Vietnamese Named Entity Recognition: Word-level vs. Character-level
• The Importance of Automatic Syntactic Features in Vietnamese Named Entity Recognition
• Error Analysis for Vietnamese Named Entity Recognition on Deep Neural Network Models
• Neural sequence labeling for Vietnamese POS Tagging and NER