Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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.
|
4 |
+
The fast speed is achieved through a combination of distillation of a compact model from the LingMess model, and an efficient batching implementation using a technique we call leftover
|
5 |
+
|
6 |
+
Please check the [official repository](https://github.com/shon-otmazgin/fastcoref) for more details and updates.
|
7 |
+
|
8 |
+
#### Experiments
|
9 |
+
|
10 |
+
| Model | Runtime | Memory |
|
11 |
+
|-----------------------|---------|---------|
|
12 |
+
| [Joshi et al. (2020)](https://arxiv.org/abs/1907.10529) | 12:06 | 27.4 |
|
13 |
+
| [Otmazgin et al. (2022)](https://arxiv.org/abs/2205.12644) | 06:43 | 4.6 |
|
14 |
+
| + Batching | 06:00 | 6.6 |
|
15 |
+
| [Kirstain et al. (2021)](https://arxiv.org/abs/2101.00434) | 04:37 | 4.4 |
|
16 |
+
| [Dobrovolskii (2021)](https://arxiv.org/abs/2109.04127) | 03:49 | 3.5 |
|
17 |
+
| [F-Coref](https://arxiv.org/abs/2209.04280) | 00:45 | 3.3 |
|
18 |
+
| + Batching | 00:35 | 4.5 |
|
19 |
+
| + Leftovers batching | 00:25 | 4.0 |
|
20 |
+
The inference time(Min:Sec) and memory(GiB) for each model on 2.8K documents. Average of 3 runs. Hardware, NVIDIA Tesla V100 SXM2.
|
21 |
+
|
22 |
+
### Citation
|