An Open-Source Dataset and A Multi-Task Model for Malay Named Entity Recognition

TL;DR

This paper introduces a new Malay NER dataset and a multi-task model with boundary detection and a gated ignoring mechanism, achieving competitive results and providing valuable resources for low-resource language NLP.

Contribution

The work presents a novel dataset construction framework for Malay NER and a multi-task model with boundary detection and error mitigation mechanisms.

Findings

The dataset MYNER contains 28,991 sentences and over 384,000 tokens.

The proposed model achieves results comparable to baseline methods on MYNER.

The dataset and model are publicly released as benchmarks.

Abstract

Named entity recognition (NER) is a fundamental task of natural language processing (NLP). However, most state-of-the-art research is mainly oriented to high-resource languages such as English and has not been widely applied to low-resource languages. In Malay language, relevant NER resources are limited. In this work, we propose a dataset construction framework, which is based on labeled datasets of homologous languages and iterative optimization, to build a Malay NER dataset (MYNER) comprising 28,991 sentences (over 384 thousand tokens). Additionally, to better integrate boundary information for NER, we propose a multi-task (MT) model with a bidirectional revision (Bi-revision) mechanism for Malay NER task. Specifically, an auxiliary task, boundary detection, is introduced to improve NER training in both explicit and implicit ways. Furthermore, a gated ignoring mechanism is proposed to conduct conditional label transfer and alleviate error propagation by the auxiliary task. Experimental results demonstrate that our model achieves comparable results over baselines on MYNER. The dataset and the model in this paper would be publicly released as a benchmark dataset.