Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
## F-Coref: Fast, Accurate and Easy to Use Coreference Resolution
|
| 2 |
|
| 3 |
[F-Coref](https://arxiv.org/abs/2209.04280) allows to process 2.8K OntoNotes documents in 25 seconds on a V100 GPU (compared to 6 minutes for the [LingMess](https://arxiv.org/abs/2205.12644) model, and to 12 minutes of the popular AllenNLP coreference model) with only a modest drop in accuracy.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- fast
|
| 7 |
+
- coreference
|
| 8 |
+
license: mit
|
| 9 |
+
datasets:
|
| 10 |
+
- multi_news
|
| 11 |
+
- ontonotes
|
| 12 |
+
metrics:
|
| 13 |
+
- CoNLL
|
| 14 |
+
task_categories:
|
| 15 |
+
- coreference_resolution
|
| 16 |
+
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
## F-Coref: Fast, Accurate and Easy to Use Coreference Resolution
|
| 20 |
|
| 21 |
[F-Coref](https://arxiv.org/abs/2209.04280) allows to process 2.8K OntoNotes documents in 25 seconds on a V100 GPU (compared to 6 minutes for the [LingMess](https://arxiv.org/abs/2205.12644) model, and to 12 minutes of the popular AllenNLP coreference model) with only a modest drop in accuracy.
|