Heuristic-enhanced Candidates Selection strategy for GPTs tackle Few-Shot Aspect-Based Sentiment Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914914540453888 |
|---|---|
| author | Jiang, Baoxing Wan, Yujie Ju, Shenggen |
| author_facet | Jiang, Baoxing Wan, Yujie Ju, Shenggen |
| contents | Few-Shot Aspect-Based Sentiment Analysis (FSABSA) is an indispensable and highly challenging task in natural language processing. However, methods based on Pre-trained Language Models (PLMs) struggle to accommodate multiple sub-tasks, and methods based on Generative Pre-trained Transformers (GPTs) perform poorly. To address the above issues, the paper designs a Heuristic-enhanced Candidates Selection (HCS) strategy and further proposes All in One (AiO) model based on it. The model works in a two-stage, which simultaneously accommodates the accuracy of PLMs and the generalization capability of GPTs. Specifically, in the first stage, a backbone model based on PLMs generates rough heuristic candidates for the input sentence. In the second stage, AiO leverages LLMs' contextual learning capabilities to generate precise predictions. The study conducted comprehensive comparative and ablation experiments on five benchmark datasets. The experimental results demonstrate that the proposed model can better adapt to multiple sub-tasks, and also outperforms the methods that directly utilize GPTs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_06063 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Heuristic-enhanced Candidates Selection strategy for GPTs tackle Few-Shot Aspect-Based Sentiment Analysis Jiang, Baoxing Wan, Yujie Ju, Shenggen Computation and Language Artificial Intelligence Machine Learning Few-Shot Aspect-Based Sentiment Analysis (FSABSA) is an indispensable and highly challenging task in natural language processing. However, methods based on Pre-trained Language Models (PLMs) struggle to accommodate multiple sub-tasks, and methods based on Generative Pre-trained Transformers (GPTs) perform poorly. To address the above issues, the paper designs a Heuristic-enhanced Candidates Selection (HCS) strategy and further proposes All in One (AiO) model based on it. The model works in a two-stage, which simultaneously accommodates the accuracy of PLMs and the generalization capability of GPTs. Specifically, in the first stage, a backbone model based on PLMs generates rough heuristic candidates for the input sentence. In the second stage, AiO leverages LLMs' contextual learning capabilities to generate precise predictions. The study conducted comprehensive comparative and ablation experiments on five benchmark datasets. The experimental results demonstrate that the proposed model can better adapt to multiple sub-tasks, and also outperforms the methods that directly utilize GPTs. |
| title | Heuristic-enhanced Candidates Selection strategy for GPTs tackle Few-Shot Aspect-Based Sentiment Analysis |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2404.06063 |