Exploring Chinese Humor Generation: A Study on Two-Part Allegorical Sayings
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929279319670784 |
|---|---|
| author | Xu, Rongwu |
| author_facet | Xu, Rongwu |
| contents | Humor, a culturally nuanced aspect of human language, poses challenges for computational understanding and generation, especially in Chinese humor, which remains relatively unexplored in the NLP community. This paper investigates the capability of state-of-the-art language models to comprehend and generate Chinese humor, specifically focusing on training them to create allegorical sayings. We employ two prominent training methods: fine-tuning a medium-sized language model and prompting a large one. Our novel fine-tuning approach incorporates fused Pinyin embeddings to consider homophones and employs contrastive learning with synthetic hard negatives to distinguish humor elements. Human-annotated results show that these models can generate humorous allegorical sayings, with prompting proving to be a practical and effective method. However, there is still room for improvement in generating allegorical sayings that match human creativity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_10781 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exploring Chinese Humor Generation: A Study on Two-Part Allegorical Sayings Xu, Rongwu Computation and Language Artificial Intelligence Humor, a culturally nuanced aspect of human language, poses challenges for computational understanding and generation, especially in Chinese humor, which remains relatively unexplored in the NLP community. This paper investigates the capability of state-of-the-art language models to comprehend and generate Chinese humor, specifically focusing on training them to create allegorical sayings. We employ two prominent training methods: fine-tuning a medium-sized language model and prompting a large one. Our novel fine-tuning approach incorporates fused Pinyin embeddings to consider homophones and employs contrastive learning with synthetic hard negatives to distinguish humor elements. Human-annotated results show that these models can generate humorous allegorical sayings, with prompting proving to be a practical and effective method. However, there is still room for improvement in generating allegorical sayings that match human creativity. |
| title | Exploring Chinese Humor Generation: A Study on Two-Part Allegorical Sayings |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2403.10781 |