An Adaptive Harmony Search Part-of-Speech tagger for Square Hmong Corpus

Authors

Di-Wen Kang, School of Communication and Electronic Engineering, Jishou University, Jishou, 416000, China.Follow
Shao-Qiang Ye, Faculty of Computing, Universiti Teknologi Malaysia, Johor, 80310, Malaysia | College of Information and Engineering, Hunan Applied Technology University, Changde, Hunan, 415000, China.Follow
Sharifah Zarith Rahmah Syed Ahmad, Faculty of Computing, Universiti Teknologi Malaysia, Johor, 80310, Malaysia.Follow
Li-Ping Mo, College of Computer Science and Engineering, Jishou University, Jishou, Hunan, 416000, China.Follow
Feng Qin, Faculty of Computing, Universiti Teknologi Malaysia, Johor, 80310, Malaysia.Follow
Pan Zhou, School of Communication and Electronic Engineering, Jishou University, Jishou, 416000, China.Follow

Abstract

Data-driven models perform poorly on part-of-speech tagging problems with the square Hmong language, a low-resource corpus. This paper designs a weight evaluation function to reduce the influence of unknown words. It proposes an improved harmony search algorithm utilizing the roulette and local evaluation strategies for handling the square Hmong part-of-speech tagging problem. The experiment shows that the average accuracy of the proposed model is 6%, 8% more than HMM and BiLSTM-CRF models, respectively. Meanwhile, the average F1 of the proposed model is also 6%, 3% more than HMM and BiLSTM-CRF models, respectively.

Keywords

Harmony Search Algorithm, Low-resource language, Optimization, Part-of-Speech tagging, Unknown words

Article Type

Special Issue Article

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite this Article

Kang, Di-Wen; Ye, Shao-Qiang; Syed Ahmad, Sharifah Zarith Rahmah; Mo, Li-Ping; Qin, Feng; and Zhou, Pan (2024) "An Adaptive Harmony Search Part-of-Speech tagger for Square Hmong Corpus," Baghdad Science Journal: Vol. 21: Iss. 2, Article 30.
DOI: https://doi.org/10.21123/bsj.2024.9694