On the Vietnamese Name Entity Recognition: A Deep Learning Method Approach

TL;DR

This paper introduces a deep learning approach combining Bi-LSTM and CRF for Vietnamese NER, utilizing word embeddings and semantic features to improve accuracy on the VLSP2016 dataset.

Contribution

It presents a novel deep learning model that integrates word embeddings, semantic, and syntactic features for Vietnamese NER, achieving state-of-the-art results.

Findings

Achieved the best results on VLSP2016 dataset

Enhanced NER accuracy with combined semantic and syntactic features

Demonstrated effectiveness of Bi-LSTM-CRF architecture for Vietnamese NER

Abstract

Named entity recognition (NER) plays an important role in text-based information retrieval. In this paper, we combine Bidirectional Long Short-Term Memory (Bi-LSTM) \cite{hochreiter1997,schuster1997} with Conditional Random Field (CRF) \cite{lafferty2001} to create a novel deep learning model for the NER problem. Each word as input of the deep learning model is represented by a Word2vec-trained vector. A word embedding set trained from about one million articles in 2018 collected through a Vietnamese news portal (baomoi.com). In addition, we concatenate a Word2Vec\cite{mikolov2013}-trained vector with semantic feature vector (Part-Of-Speech (POS) tagging, chunk-tag) and hidden syntactic feature vector (extracted by Bi-LSTM nerwork) to achieve the (so far best) result in Vietnamese NER system. The result was conducted on the data set VLSP2016 (Vietnamese Language and Speech Processing 2016 \cite{vlsp2016}) competition.