Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,28 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
| 4 |
+
|
| 5 |
+
This a reproduction of the following paper:
|
| 6 |
+
```
|
| 7 |
+
@inproceedings{katsumata-komachi-2020-stronger,
|
| 8 |
+
title = "Stronger Baselines for Grammatical Error Correction Using a Pretrained Encoder-Decoder Model",
|
| 9 |
+
author = "Katsumata, Satoru and
|
| 10 |
+
Komachi, Mamoru",
|
| 11 |
+
booktitle = "Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing",
|
| 12 |
+
month = dec,
|
| 13 |
+
year = "2020",
|
| 14 |
+
address = "Suzhou, China",
|
| 15 |
+
publisher = "Association for Computational Linguistics",
|
| 16 |
+
url = "https://aclanthology.org/2020.aacl-main.83",
|
| 17 |
+
pages = "827--832",
|
| 18 |
+
}
|
| 19 |
+
```
|
| 20 |
+
|
| 21 |
+
This model achieves the following results:
|
| 22 |
+
|Data|Metric|gotutiyan/gec-bart-base|
|
| 23 |
+
|:--|:--|:--|
|
| 24 |
+
|CoNLL-2014|M2 (P/R/F0.5)|70.0 / 38.5 / 60.2|
|
| 25 |
+
|BEA19-test|ERRANT (P/R/F0.5)|67.7 / 50.1 / 63.3|
|
| 26 |
+
|JFLEG-test|GLEU|55.2|
|
| 27 |
+
|
| 28 |
+
The details can be found in the [GitHub repository](https://github.com/gotutiyan/GEC-BART).
|