Artifact AI
commited on
Commit
·
86117e1
1
Parent(s):
f486984
add readme
Browse files
README.md
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: en
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
## Introduction
|
| 7 |
+
|
| 8 |
+
A led-base-16384 model to summarize ArXiv papers. Inputs are the abstracts of papers and full documents, and outputs are the summaries of the papers.
|
| 9 |
+
|
| 10 |
+
[Allenai's Longformer Encoder-Decoder (LED)](https://github.com/allenai/longformer#longformer).
|
| 11 |
+
|
| 12 |
+
As described in [Longformer: The Long-Document Transformer](https://arxiv.org/pdf/2004.05150.pdf) by Iz Beltagy, Matthew E. Peters, Arman Cohan, *led-base-16384* was initialized from [*bart-base*](https://huggingface.co/facebook/bart-base) since both models share the exact same architecture. To be able to process 16K tokens, *bart-base*'s position embedding matrix was simply copied 16 times.
|
| 13 |
+
|
| 14 |
+
### Rouge
|
| 15 |
+
|
| 16 |
+
| Type | Score |
|
| 17 |
+
| --- | --- |
|
| 18 |
+
| `precision` | 0.1839148953011932 |
|
| 19 |
+
| `recall` | 0.14904707945189774 |
|
| 20 |
+
| `fmeasure` | 0.1580026685776864 |
|