alemiaschi
commited on
Commit
•
6f840f1
1
Parent(s):
c64d246
Update README.md
Browse files
README.md
CHANGED
@@ -11,3 +11,27 @@ widget:
|
|
11 |
|
12 |
# Li-IT5 Small
|
13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
|
12 |
# Li-IT5 Small
|
13 |
|
14 |
+
This model is released as part of the paper "Linguistic Knowledge Can Enhance Encoder-Decoder Models (If You Let It)" (Miaschi et al., 2024).
|
15 |
+
If you use this model in your work, we kindly ask you to cite our paper:
|
16 |
+
|
17 |
+
```bibtex
|
18 |
+
@inproceedings{miaschi_linguistic_knowledge,
|
19 |
+
title = "Linguistic Knowledge Can Enhance Encoder-Deocer Models (If You Let It)",
|
20 |
+
author = "Miaschi, Alessio and Dell'Orletta Felice and Venturi, Giulia",
|
21 |
+
}
|
22 |
+
```
|
23 |
+
|
24 |
+
Other information can be found in the original [GitHub repository](https://github.com/alemiaschi/linguistically_informed_t5/tree/main).
|
25 |
+
|
26 |
+
## Model Description
|
27 |
+
|
28 |
+
The model is based on a T5 model fine-tuned in a multitask fashion to solve a set of raw, morpho-syntactic and syntactic tasks (i.e. predictions of linguistic properties).
|
29 |
+
The full list of the 10 linguistic properties used as intermediate tasks can be found in the original paper.
|
30 |
+
|
31 |
+
This model is based on the Italian version of t5-small, [it5-small](https://huggingface.co/gsarti/it5-small).
|
32 |
+
|
33 |
+
## Model variations
|
34 |
+
|
35 |
+
The other fine-tuned models presented in the original study are the following:
|
36 |
+
|
37 |
+
- [li-it5-base]()
|