FPT: Feature Prompt Tuning for Few-shot Readability Assessment
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911833851428864 |
|---|---|
| author | Wang, Ziyang Lee, Sanwoo Huang, Hsiu-Yuan Wu, Yunfang |
| author_facet | Wang, Ziyang Lee, Sanwoo Huang, Hsiu-Yuan Wu, Yunfang |
| contents | Prompt-based methods have achieved promising results in most few-shot text classification tasks. However, for readability assessment tasks, traditional prompt methods lackcrucial linguistic knowledge, which has already been proven to be essential. Moreover, previous studies on utilizing linguistic features have shown non-robust performance in few-shot settings and may even impair model performance.To address these issues, we propose a novel prompt-based tuning framework that incorporates rich linguistic knowledge, called Feature Prompt Tuning (FPT). Specifically, we extract linguistic features from the text and embed them into trainable soft prompts. Further, we devise a new loss function to calibrate the similarity ranking order between categories. Experimental results demonstrate that our proposed method FTP not only exhibits a significant performance improvement over the prior best prompt-based tuning approaches, but also surpasses the previous leading methods that incorporate linguistic features. Also, our proposed model significantly outperforms the large language model gpt-3.5-turbo-16k in most cases. Our proposed method establishes a new architecture for prompt tuning that sheds light on how linguistic features can be easily adapted to linguistic-related tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_02772 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FPT: Feature Prompt Tuning for Few-shot Readability Assessment Wang, Ziyang Lee, Sanwoo Huang, Hsiu-Yuan Wu, Yunfang Computation and Language Prompt-based methods have achieved promising results in most few-shot text classification tasks. However, for readability assessment tasks, traditional prompt methods lackcrucial linguistic knowledge, which has already been proven to be essential. Moreover, previous studies on utilizing linguistic features have shown non-robust performance in few-shot settings and may even impair model performance.To address these issues, we propose a novel prompt-based tuning framework that incorporates rich linguistic knowledge, called Feature Prompt Tuning (FPT). Specifically, we extract linguistic features from the text and embed them into trainable soft prompts. Further, we devise a new loss function to calibrate the similarity ranking order between categories. Experimental results demonstrate that our proposed method FTP not only exhibits a significant performance improvement over the prior best prompt-based tuning approaches, but also surpasses the previous leading methods that incorporate linguistic features. Also, our proposed model significantly outperforms the large language model gpt-3.5-turbo-16k in most cases. Our proposed method establishes a new architecture for prompt tuning that sheds light on how linguistic features can be easily adapted to linguistic-related tasks. |
| title | FPT: Feature Prompt Tuning for Few-shot Readability Assessment |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2404.02772 |