DaryaTereshchenko
commited on
Commit
·
00ed639
1
Parent(s):
2d9442e
Updated README file with references to the paper and repo
Browse files
README.md
CHANGED
|
@@ -48,6 +48,8 @@ This repository contains the `Prism` model, a state-of-the-art multilingual neur
|
|
| 48 |
|
| 49 |
The model was trained with a focus on multilingual performance, excelling in tasks such as translation quality estimation and evaluation, making it a versatile choice for research and practical use in various language pairs.
|
| 50 |
|
|
|
|
|
|
|
| 51 |
## Model Description
|
| 52 |
|
| 53 |
The `Prism` model was designed to be a lexically/syntactically unbiased paraphraser. The core idea is to treat paraphrasing as a zero-shot translation task, which allows the model to cover a wide range of languages effectively.
|
|
|
|
| 48 |
|
| 49 |
The model was trained with a focus on multilingual performance, excelling in tasks such as translation quality estimation and evaluation, making it a versatile choice for research and practical use in various language pairs.
|
| 50 |
|
| 51 |
+
It was introduced in this [paper](https://aclanthology.org/2020.emnlp-main.8.pdf) and first released in [this](https://github.com/thompsonb/prism/tree/master) repository.
|
| 52 |
+
|
| 53 |
## Model Description
|
| 54 |
|
| 55 |
The `Prism` model was designed to be a lexically/syntactically unbiased paraphraser. The core idea is to treat paraphrasing as a zero-shot translation task, which allows the model to cover a wide range of languages effectively.
|