%A Ngoc Vu Nguyen
%A Thi Lan Nguyen
%A Thi Cam Van Nguyen
%A Mai Vu Tran
%A Quang Thuy Ha
%T A Character-Level Deep Lifelong Learning Model for Named Entity Recognition in Vietnamese Text
%X Lifelong Machine Learning (LML) is a continuous learning process, in which the knowledge learned from previous tasks is accumulated in the knowledge base, then the knowledge will be used to support future learning tasks, for which it may be only a few of samples exists. However, there is a little of studies on LML based on deep neural networks for Named Entity Recognition (NER), especial in Vietnamese. We propose DeepLML-NER model, a lifelong learning model based on using deep learning methods with a CRFs layer, for NER in Vietnamese text. DeepLML-NER includes an algorithm to extract the knowledge of “prefix-features” of Named Entities in previous domains. Then the model uses the knowledge stored in the knowledge base to solve a new NER task. The effect of the model was demonstrated by in-domain and cross-domain experiments, achieving promising results.
%C Yogyakarta, Indonesia
%D 2019
%P 90-102
%L SisLab3471