How well ChatGPT understand Malaysian English? An Evaluation on Named Entity Recognition and Relation Extraction
This work addresses the problem of assessing AI model robustness for non-standard English variants, which is incremental as it extends existing evaluations to a specific domain.
The study evaluated ChatGPT's performance on Named Entity Recognition and Relation Extraction for Malaysian English, finding it performed poorly on entity extraction with a maximum F1-Score of 0.497, but relation extraction was unaffected.
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.