SinclairWang
commited on
Commit
•
b829bc1
1
Parent(s):
38ffcba
Update README.md
Browse files
README.md
CHANGED
@@ -8,4 +8,20 @@ metrics:
|
|
8 |
- f1
|
9 |
- exact_match
|
10 |
library_name: transformers
|
11 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
- f1
|
9 |
- exact_match
|
10 |
library_name: transformers
|
11 |
+
---
|
12 |
+
|
13 |
+
|
14 |
+
# Restaurant-T5-Base
|
15 |
+
|
16 |
+
|
17 |
+
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.
|
18 |
+
|
19 |
+
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).
|
20 |
+
|
21 |
+
|
22 |
+
# Model Description
|
23 |
+
|
24 |
+
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*,
|
25 |
+
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*
|
26 |
+
(corruption rate of 15% and average span length of 1).
|
27 |
+
|