Can ChatGPT Understand Malapropism Correctly? Challenges to Davidson's Passing Theory in Generative AI
- Tsukasa Yamanaka
Abstract
This study examines ChatGPT's performance in understanding Japanese malapropisms, aiming to explore its capacity for linguistic inference compared to humans. Despite its remarkable fluency in conversation, ChatGPT shows significant limitations in comprehending malapropisms, particularly in handling phonetic, lexical, and contextual errors. Using a specialized dataset, the research highlights these gaps, suggesting that while ChatGPT excels in fluency, its understanding of nuanced language phenomena remains distinct from human comprehension. The findings contribute to the discourse on the potential and limitations of generative AI, advocating for a reevaluation of linguistic-philosophical theories in light of AI advancements.
- Full Text:
PDF
- DOI:10.5539/elt.v17n9p48
Journal Metrics
Index
- Academic Journals Database
- CNKI Scholar
- Educational Research Abstracts
- Elektronische Zeitschriftenbibliothek (EZB)
- EuroPub Database
- Excellence in Research for Australia (ERA)
- GETIT@YALE (Yale University Library)
- Harvard Library E-Journals
- IBZ Online
- INDEX ISLAMICUS
- JournalSeek
- JournalTOCs
- LearnTechLib
- Linguistics Abstracts Online
- LOCKSS
- MIAR
- MLA International Bibliography
- NewJour
- Open J-Gate
- PKP Open Archives Harvester
- Publons
- ResearchGate
- ROAD
- SHERPA/RoMEO
- Standard Periodical Directory
- Technische Informationsbibliothek (TIB)
- The Keepers Registry
- Ulrich's
- Universe Digital Library
Contact
- Gavin YuEditorial Assistant
- elt@ccsenet.org