Span Labeling Approach for Vietnamese and Chinese Word Segmentation

TL;DR

This paper introduces a span labeling method for Vietnamese and Chinese word segmentation that outperforms traditional sequence tagging, achieving state-of-the-art results with faster inference and fewer parameters.

Contribution

The paper presents a novel span labeling approach for word segmentation, demonstrating superior performance over sequence tagging methods on Vietnamese and Chinese datasets.

Findings

Achieved 98.31% F-score on Vietnamese benchmark.

Outperformed previous methods on five Chinese benchmarks.

Faster inference with fewer parameters using BERT and ZEN models.

Abstract

In this paper, we propose a span labeling approach to model n-gram information for Vietnamese word segmentation, namely SPAN SEG. We compare the span labeling approach with the conditional random field by using encoders with the same architecture. Since Vietnamese and Chinese have similar linguistic phenomena, we evaluated the proposed method on the Vietnamese treebank benchmark dataset and five Chinese benchmark datasets. Through our experimental results, the proposed approach SpanSeg achieves higher performance than the sequence tagging approach with the state-of-the-art F-score of 98.31% on the Vietnamese treebank benchmark, when they both apply the contextual pre-trained language model XLM-RoBERTa and the predicted word boundary information. Besides, we do fine-tuning experiments for the span labeling approach on BERT and ZEN pre-trained language model for Chinese with fewer parameters, faster inference time, and competitive or higher F-scores than the previous state-of-the-art approach, word segmentation with word-hood memory networks, on five Chinese benchmarks.