Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,23 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- inseq/scat
|
| 5 |
+
- gsarti/iwslt2017_context
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
+
- fr
|
| 9 |
+
pipeline_tag: translation
|
| 10 |
+
tags:
|
| 11 |
+
- arxiv:2310.01188
|
| 12 |
+
- contextual-mt
|
| 13 |
+
- document-mt
|
| 14 |
---
|
| 15 |
+
|
| 16 |
+
*This model corresponds to the [`Helsinki-NLP/opus-mt-tc-big-en-fr`](https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-en-fr) further trained on English-to-French translation on the [IWSLT17 dataset](https://huggingface.co/datasets/gsarti/iwslt2017_context) with context tags using the format:
|
| 17 |
+
|
| 18 |
+
```
|
| 19 |
+
Input: SOURCE_CTX <brk> SOURCE_CURR
|
| 20 |
+
Output: TARGET_CTX <brk> TARGET_CURR
|
| 21 |
+
```
|
| 22 |
+
|
| 23 |
+
and further fine-tuned on the training split of [SCAT+](https://huggingface.co/datasets/inseq/scat). The model was used in the evaluation of the paper [Quantifying the Plausibility of Context Reliance in Neural Machine Translation](https://openreview.net/forum?id=XTHfNGI3zT) published at ICLR 2024, also available on [Arxiv](https://arxiv.org/abs/2310.01188). It can be used for English to French contextual and non-contextual translation.
|