|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- jakartaresearch/semeval-absa |
|
language: |
|
- en |
|
metrics: |
|
- f1 |
|
- exact_match |
|
library_name: transformers |
|
--- |
|
|
|
|
|
# Restaurant-T5-Base |
|
|
|
|
|
The Restaurant-T5-Base model was introduced in [A Simple yet Effective Framework for Few-Shot Aspect-Based Sentiment Analysis (SIGIR'23)](https://doi.org/10.1145/3539618.3591940) by Zengzhi Wang, Qiming Xie, and Rui Xia. |
|
|
|
The details are available at [Github:FS-ABSA](https://github.com/nustm/fs-absa) and [SIGIR'23 paper](https://doi.org/10.1145/3539618.3591940). |
|
|
|
|
|
# Model Description |
|
|
|
To bridge the domain gap between general pre-training and the task of interest in a specific domain (i.e., `restaurant` in this repo), we conducted *domain-adaptive pre-training*, |
|
continuing pre-training the language model (i.e., T5) on the unlabeled corpus of the domain of interest (i.e., `restaurant`) with the *text-infilling objective* |
|
(corruption rate of 15% and average span length of 1). |
|
|
|
|
