Assessing the potential of LLM-assisted annotation for corpus-based pragmatics and discourse analysis
The case of apology
Certain forms of linguistic annotation, like part of speech and semantic tagging, can be automated with high accuracy. However, manual annotation is still necessary for complex pragmatic and discursive features that lack a direct mapping to lexical forms. This manual process is time-consuming and error-prone, limiting the scalability of function-to-form approaches in corpus linguistics. To address this, our study explores the possibility of using large language models (LLMs) to automate pragma-discursive corpus annotation. We compare GPT-3.5 (the model behind the free-to-use version of ChatGPT), GPT-4 (the model underpinning the precise mode of Bing chatbot), and a human coder in annotating apology components in English based on the local grammar framework. We find that GPT-4 outperformed GPT-3.5, with accuracy approaching that of a human coder. These results suggest that LLMs can be successfully deployed to aid pragma-discursive corpus annotation, making the process more efficient, scalable, and accessible.
Article outline
- 1.Introduction
- 2.Corpus annotation: Long-standing challenges, new opportunities
- 2.1Challenges in automating pragmatic and discourse-level annotation
- 2.2LLM-assisted corpus annotation
- 3.Data and methods
- 3.1The annotation task
- 3.2Prompt design
- 3.3Performance evaluation
- 4.Results
- 4.1GPT-3.5 versus GPT-4
- 4.2GPT-4 versus a human annotator
- 4.2.1Recognition of no apology
- 4.2.2Recognition of apologising
- 4.2.3Recognition of reason
- 4.2.4Recognition of apologiser
- 4.2.5Recognition of apologisee
- 4.2.6Recognition of intensifier
- 4.3Summary of findings
- 5.Conclusion
- Notes
-
References