Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: mit
|
5 |
+
tags:
|
6 |
+
- GECToR
|
7 |
+
- Grammar Error Correction
|
8 |
+
- xlnet-base-cased
|
9 |
+
pipeline_tag: token-classification
|
10 |
+
---
|
11 |
+
|
12 |
+
### License
|
13 |
+
The model is licensed under the MIT License
|
14 |
+
### Sample Code
|
15 |
+
|
16 |
+
### Citation
|
17 |
+
|
18 |
+
You can find the original code at https://github.com/grammarly/gector
|
19 |
+
|
20 |
+
You can find the paper at https://aclanthology.org/2020.bea-1.16/
|
21 |
+
|
22 |
+
```bib
|
23 |
+
@inproceedings{omelianchuk-etal-2020-gector,
|
24 |
+
title = "{GECT}o{R} {--} Grammatical Error Correction: Tag, Not Rewrite",
|
25 |
+
author = "Omelianchuk, Kostiantyn and
|
26 |
+
Atrasevych, Vitaliy and
|
27 |
+
Chernodub, Artem and
|
28 |
+
Skurzhanskyi, Oleksandr",
|
29 |
+
booktitle = "Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications",
|
30 |
+
month = jul,
|
31 |
+
year = "2020",
|
32 |
+
address = "Seattle, WA, USA → Online",
|
33 |
+
publisher = "Association for Computational Linguistics",
|
34 |
+
url = "https://www.aclweb.org/anthology/2020.bea-1.16",
|
35 |
+
pages = "163--170",
|
36 |
+
abstract = "In this paper, we present a simple and efficient GEC sequence tagger using a Transformer encoder. Our system is pre-trained on synthetic data and then fine-tuned in two stages: first on errorful corpora, and second on a combination of errorful and error-free parallel corpora. We design custom token-level transformations to map input tokens to target corrections. Our best single-model/ensemble GEC tagger achieves an F{\_}0.5 of 65.3/66.5 on CONLL-2014 (test) and F{\_}0.5 of 72.4/73.6 on BEA-2019 (test). Its inference speed is up to 10 times as fast as a Transformer-based seq2seq GEC system.",
|
37 |
+
}
|
38 |
+
```
|