Answers are grounded in this paper and cite their sources.
The rapid advancement of technology has led to the development of intelligent software tools that can almost impersonate humans in understanding human language. This has led to a significant advancement in natural language processing (NLP), which combines artificial intelligence with computational linguistics to produce and understand natural languages. The question remains whether these tools can handle the complexity of human language. To determine this, two types of human language, metaphors and idioms, were collected to test the ability of modern AI tools, ChatGPT and Google Bard, in understanding figurative language correctly. These complex languages require advanced intellectual abilities to comprehend. The data included sample sentences from both English and Turkish. Although their performance with metaphors was not as good as with idioms, the findings demonstrated that these AI-powered chatbots have a near-human knowledge of language, showing a high level of proficiency in processing human language.
No takes yet. Share an insight, caveat, or question.
Abdulrahman Alhaydar (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: