Weerayut Buaphet
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Weerayut Buaphet has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Sarana Nutanong
School of Information Science and Technology, Vidyasirimedhi Institute of Science and Technology, Rayong, Thailand
2 shared publications - Attapol Thamrongrattanarit-Rutherford
Department of Linguistics, Chulalongkorn University, Bangkok, Thailand
1 shared publication Can Udomcharoenchaikit
School of Information Science and Technology, VISTEC, Rayong, Thailand
1 shared publication- Holy Lovenia
SeaCrowd
1 shared publication - Hwanhee Lee
Chung-Ang University Seoul Korea
1 shared publication - Jimin Lee
Chung-Ang University
1 shared publication
Latest Publications
- Open Access
- 9 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 25 (7) , 1-14
MultiLexNorm++: A Unified Benchmark and a Generative Model for Lexical Normalization for Asian Languages
Social media data has been of interest to Natural Language Processing (NLP) practitioners for over a decade, because of its richness in information, but also challenges for automatic processing. Since language use is more informal, spontaneous, and adheres to many different sociolects, the performance of NLP models often deteriorates. One solution to this problem is to transform data to a standard variant before processing it, which is also called lexical normalization. There has been a wide variety of benchmarks and models proposed for this task. The MultiLexNorm benchmark proposed to unify these efforts, but it consists almost solely of languages from the Indo-European language family in the Latin script. Hence, we propose an extension to MultiLexNorm, which covers five Asian languages from different language families in four different scripts. We show that the previous state-of-the-art model performs worse on the new languages and propose a new architecture based on Large Language Models (LLMs), which shows more robust performance. Finally, we analyze remaining errors, revealing future directions for this task.
- 9 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 25 (7) , 1-14
Open AccessMultiLexNorm++: A Unified Benchmark and a Generative Model for Lexical Normalization for Asian Languages
Social media data has been of interest to Natural Language Processing (NLP) practitioners for over a decade, because of its richness in information, but also challenges for automatic processing. Since language use is more informal, spontaneous, and adheres to many different sociolects, the performance of NLP models often deteriorates. One solution to this problem is to transform data to a standard variant before processing it, which is also called lexical normalization. There has been a wide variety of benchmarks and models proposed for this task. The MultiLexNorm benchmark proposed to unify these efforts, but it consists almost solely of languages from the Indo-European language family in the Latin script. Hence, we propose an extension to MultiLexNorm, which covers five Asian languages from different language families in four different scripts. We show that the previous state-of-the-art model performs worse on the new languages and propose a new architecture based on Large Language Models (LLMs), which shows more robust performance. Finally, we analyze remaining errors, revealing future directions for this task.
- Open Access
- 11 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 198792-198811
LLM-Augmented Prototype Representation for Few-Shot Named-Entity Recognition
Named Entity Recognition (NER) models face challenges in adapting to data distribution shifts, especially with unseen entity types and limited data. Few-shot learning is used to address long-tailed distributions and unseen classes, but struggles with few labeled examples, leading to inaccurate prototypes. Recently, Large Language Models (LLMs) excel at Few-Shot Named Entity Recognition (FS-NER) via in-context learning, but their substantially higher computational cost and latency compared to prototype-based models limit their practicality for resource-constrained or real-time applications. In this paper, we propose a new way to use LLMs to augment the FS-NER system and a way for the prototype network to utilize the augmented dataset. We aim to examine whether LLM In-context learning (LLM-ICL) can effectively replace the encoder model in the FS-NER task. We study an LLM-based data augmentation framework that generates new mentions and descriptions for specific entity types when fine-tuning, while maintaining inference-time efficiency, improving the robustness of embeddings and prototype representations. Our method shows consistent improvements across FS-NER setups, demonstrating the potential of LLMs as external knowledge sources for NER.
- 11 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 198792-198811
Open AccessLLM-Augmented Prototype Representation for Few-Shot Named-Entity Recognition
Named Entity Recognition (NER) models face challenges in adapting to data distribution shifts, especially with unseen entity types and limited data. Few-shot learning is used to address long-tailed distributions and unseen classes, but struggles with few labeled examples, leading to inaccurate prototypes. Recently, Large Language Models (LLMs) excel at Few-Shot Named Entity Recognition (FS-NER) via in-context learning, but their substantially higher computational cost and latency compared to prototype-based models limit their practicality for resource-constrained or real-time applications. In this paper, we propose a new way to use LLMs to augment the FS-NER system and a way for the prototype network to utilize the augmented dataset. We aim to examine whether LLM In-context learning (LLM-ICL) can effectively replace the encoder model in the FS-NER task. We study an LLM-based data augmentation framework that generates new mentions and descriptions for specific entity types when fine-tuning, while maintaining inference-time efficiency, improving the robustness of embeddings and prototype representations. Our method shows consistent improvements across FS-NER setups, demonstrating the potential of LLMs as external knowledge sources for NER.