Hierarchical Transformer Encoders for Vietnamese Spelling Correction

TL;DR

This paper introduces a hierarchical Transformer model for Vietnamese spelling correction that leverages character and word levels, along with a new real-life dataset, achieving superior performance over existing methods.

Contribution

The paper presents a novel hierarchical Transformer architecture and a realistic Vietnamese spelling correction dataset, advancing the state-of-the-art in accuracy and practical applicability.

Findings

Outperforms existing methods in recall, precision, and F1-score

Introduces a new real-life Vietnamese spelling correction dataset

Demonstrates effectiveness of hierarchical Transformer approach

Abstract

In this paper, we propose a Hierarchical Transformer model for Vietnamese spelling correction problem. The model consists of multiple Transformer encoders and utilizes both character-level and word-level to detect errors and make corrections. In addition, to facilitate future work in Vietnamese spelling correction tasks, we propose a realistic dataset collected from real-life texts for the problem. We compare our method with other methods and publicly available systems. The proposed method outperforms all of the contemporary methods in terms of recall, precision, and f1-score. A demo version is publicly available.