DuanzAI: Slang-Enhanced LLM with Prompt for Humor Understanding
This work addresses the challenge of slang and humor understanding in digital communication for Chinese language users, representing an incremental improvement in domain-specific AI applications.
The paper tackled the problem of AI models struggling to understand Chinese slang and humor by developing DuanzAI, an enhanced LLM approach that improved comprehension through curated datasets and techniques like Punchline Entity Recognition, resulting in contextually relevant responses.
Language's complexity is evident in the rich tapestry of slang expressions, often laden with humor and cultural nuances. This linguistic phenomenon has become increasingly prevalent, especially in digital communication. However, existing AI models, including ChatGPT-3.5, face challenges in comprehending these nuances, particularly in Chinese slang. In this study, we present DuanzAI, an innovative approach enhancing Large Language Models (LLMs) with deep Chinese slang comprehension. Leveraging curated datasets and advanced techniques, DuanzAI bridges the gap between human expression and AI comprehension, enabling contextually relevant responses. Our experiments contrast LLMs' performance with a custom Punchline Entity Recognition (PER) system, integrating phonetic matching and pinyin2hanzi techniques. Applying these insights, we developed ChatDAI, an advanced chatbot and released our code at \url{https://github.com/YesianRohn/DuanzAI}.