LSTM Easy-first Dependency Parsing with Pre-trained Word Embeddings and Character-level Word Embeddings in Vietnamese

TL;DR

This paper introduces an LSTM-based easy-first dependency parser for Vietnamese that leverages pre-trained and character-level embeddings, achieving state-of-the-art accuracy on the Vietnamese Dependency Treebank.

Contribution

It presents a novel combination of LSTM easy-first parsing with pre-trained and character-level embeddings specifically for Vietnamese dependency parsing.

Findings

Achieved 80.91% UAS on VnDT

Achieved 72.98% LAS on VnDT

Demonstrated effectiveness of combined embeddings in Vietnamese parsing

Abstract

In Vietnamese dependency parsing, several methods have been proposed. Dependency parser which uses deep neural network model has been reported that achieved state-of-the-art results. In this paper, we proposed a new method which applies LSTM easy-first dependency parsing with pre-trained word embeddings and character-level word embeddings. Our method achieves an accuracy of 80.91% of unlabeled attachment score and 72.98% of labeled attachment score on the Vietnamese Dependency Treebank (VnDT).