How well ChatGPT understand Malaysian English? An Evaluation on Named Entity Recognition and Relation Extraction

TL;DR

This study evaluates ChatGPT's ability to perform named entity recognition and relation extraction on Malaysian English news, revealing limitations in entity extraction due to linguistic adaptations but not in relation extraction.

Contribution

It introduces a novel evaluation methodology and provides insights into ChatGPT's performance on Malaysian English, highlighting linguistic challenges affecting entity recognition.

Findings

ChatGPT's highest F1-Score for entity extraction is 0.497.

Morphosyntactic adaptation in Malaysian English limits entity extraction.

Relation extraction performance remains unaffected by linguistic differences.

Abstract

Recently, ChatGPT has attracted a lot of interest from both researchers and the general public. While the performance of ChatGPT in named entity recognition and relation extraction from Standard English texts is satisfactory, it remains to be seen if it can perform similarly for Malaysian English. Malaysian English is unique as it exhibits morphosyntactic and semantical adaptation from local contexts. In this study, we assess ChatGPT's capability in extracting entities and relations from the Malaysian English News (MEN) dataset. We propose a three-step methodology referred to as \textbf{\textit{educate-predict-evaluate}}. The performance of ChatGPT is assessed using F1-Score across 18 unique prompt settings, which were carefully engineered for a comprehensive review. From our evaluation, we found that ChatGPT does not perform well in extracting entities from Malaysian English news articles, with the highest F1-Score of 0.497. Further analysis shows that the morphosyntactic adaptation in Malaysian English caused the limitation. However, interestingly, this morphosyntactic adaptation does not impact the performance of ChatGPT for relation extraction.