NNVLP: A Neural Network-Based Vietnamese Language Processing Toolkit

TL;DR

This paper introduces NNVLP, a neural network toolkit for Vietnamese language processing that combines Bi-LSTM, CNN, and CRF to achieve state-of-the-art results in POS tagging, chunking, and NER.

Contribution

The paper presents a novel neural network-based toolkit specifically designed for Vietnamese language processing, integrating multiple deep learning models for improved performance.

Findings

Achieves state-of-the-art results on Vietnamese POS tagging, chunking, and NER.

Provides accessible API and web demo for practical use.

Demonstrates effectiveness of combining Bi-LSTM, CNN, and CRF models.

Abstract

This paper demonstrates neural network-based toolkit namely NNVLP for essential Vietnamese language processing tasks including part-of-speech (POS) tagging, chunking, named entity recognition (NER). Our toolkit is a combination of bidirectional Long Short-Term Memory (Bi-LSTM), Convolutional Neural Network (CNN), Conditional Random Field (CRF), using pre-trained word embeddings as input, which achieves state-of-the-art results on these three tasks. We provide both API and web demo for this toolkit.