Paula Leonova
commited on
Commit
•
149a1e5
1
Parent(s):
40a3947
Update Readme
Browse files
README.md
CHANGED
|
@@ -9,13 +9,13 @@ pinned: false
|
|
| 9 |
---
|
| 10 |
|
| 11 |
#### Interactive version
|
| 12 |
-
This app is hosted on https://huggingface.co/spaces/pleonova/multi-label-summary-text
|
| 13 |
|
| 14 |
#### Objective
|
| 15 |
-
|
| 16 |
|
| 17 |
#### Model
|
| 18 |
-
facebook/bart-large-mnli zero-shot learning summarizer and classifier
|
| 19 |
|
| 20 |
#### Approach
|
| 21 |
Updating the head of the neural network, we can use the same pretrained bart model to first summarize our long text by first splitting out our long text into chunks of 1024 tokens and then generating a summary for each of the text chunks. Next, all the summaries are concanenated and the bart model is used classify the summarized text. Alternatively, one can also classify the whole text as is.
|
| 9 |
---
|
| 10 |
|
| 11 |
#### Interactive version
|
| 12 |
+
This app is hosted on HuggingFace spaces: https://huggingface.co/spaces/pleonova/multi-label-summary-text
|
| 13 |
|
| 14 |
#### Objective
|
| 15 |
+
The goal of this app is to identify multiple relevant labels for long text.
|
| 16 |
|
| 17 |
#### Model
|
| 18 |
+
facebook/bart-large-mnli zero-shot transfer-learning summarizer and classifier
|
| 19 |
|
| 20 |
#### Approach
|
| 21 |
Updating the head of the neural network, we can use the same pretrained bart model to first summarize our long text by first splitting out our long text into chunks of 1024 tokens and then generating a summary for each of the text chunks. Next, all the summaries are concanenated and the bart model is used classify the summarized text. Alternatively, one can also classify the whole text as is.
|