Prompting Implicit Discourse Relation Annotation
This work addresses a specific challenge in natural language processing for researchers, showing incremental progress by highlighting limitations in current prompting methods for discourse analysis.
The study tackled the problem of ChatGPT's poor performance in implicit discourse relation classification by testing various prompting techniques, but found that even sophisticated prompt engineering did not significantly improve accuracy, indicating the task remains unresolved in zero-shot or few-shot settings.
Pre-trained large language models, such as ChatGPT, archive outstanding performance in various reasoning tasks without supervised training and were found to have outperformed crowdsourcing workers. Nonetheless, ChatGPT's performance in the task of implicit discourse relation classification, prompted by a standard multiple-choice question, is still far from satisfactory and considerably inferior to state-of-the-art supervised approaches. This work investigates several proven prompting techniques to improve ChatGPT's recognition of discourse relations. In particular, we experimented with breaking down the classification task that involves numerous abstract labels into smaller subtasks. Nonetheless, experiment results show that the inference accuracy hardly changes even with sophisticated prompt engineering, suggesting that implicit discourse relation classification is not yet resolvable under zero-shot or few-shot settings.