DeDeckerThomas
commited on
Commit
Β·
958ab29
1
Parent(s):
c548eef
Update README.md
Browse files
README.md
CHANGED
@@ -33,10 +33,11 @@ model-index:
|
|
33 |
value: 0.080
|
34 |
name: F1@O (A)
|
35 |
---
|
|
|
36 |
# π Keyphrase Generation model: KeyBART-inspec
|
37 |
Keyphrase extraction is a technique in text analysis where you extract the important keyphrases from a text. Since this is a time-consuming process, Artificial Intelligence is used to automate it.
|
38 |
Currently, classical machine learning methods, that use statistics and linguistics, are widely used for the extraction process. The fact that these methods have been widely used in the community has the advantage that there are many easy-to-use libraries.
|
39 |
-
Now with the recent innovations in deep learning methods (such as recurrent neural networks and transformers, GANS, β¦), keyphrase extraction can be improved. These new methods also focus on the semantics and context of a document, which is quite an improvement. Thanks to the introduction of
|
40 |
|
41 |
## π Model Description
|
42 |
This model is a fine-tuned KeyBART model on the Inspec dataset.
|
@@ -139,13 +140,13 @@ One of the traditional evaluation methods is the precision, recall and F1-score
|
|
139 |
The model achieves the following results on the Inspec test set:
|
140 |
|
141 |
|
142 |
-
Extractive keyphrases
|
143 |
|
144 |
| Dataset | P@5 | R@5 | F1@5 | P@10 | R@10 | F1@10 | P@M | R@M | F1@M | P@O | R@O | F1@O |
|
145 |
|:-----------------:|:----:|:----:|:----:|:----:|:----:|:-----:|:----:|:----:|:----:|:----:|:----:|:----:|
|
146 |
| Inspec Test Set | 0.40 | 0.37 | 0.35 | 0.20 | 0.37 | 0.24 | 0.42 | 0.37 | 0.36 | 0.33 | 0.33 | 0.33 |
|
147 |
|
148 |
-
Abstractive keyphrases
|
149 |
|
150 |
| Dataset | P@5 | R@5 | F1@5 | P@10 | R@10 | F1@10 | P@M | R@M | F1@M | P@O | R@O | F1@O |
|
151 |
|:-----------------:|:----:|:----:|:----:|:----:|:----:|:-----:|:----:|:----:|:----:|:----:|:----:|:----:|
|
|
|
33 |
value: 0.080
|
34 |
name: F1@O (A)
|
35 |
---
|
36 |
+
|
37 |
# π Keyphrase Generation model: KeyBART-inspec
|
38 |
Keyphrase extraction is a technique in text analysis where you extract the important keyphrases from a text. Since this is a time-consuming process, Artificial Intelligence is used to automate it.
|
39 |
Currently, classical machine learning methods, that use statistics and linguistics, are widely used for the extraction process. The fact that these methods have been widely used in the community has the advantage that there are many easy-to-use libraries.
|
40 |
+
Now with the recent innovations in deep learning methods (such as recurrent neural networks and transformers, GANS, β¦), keyphrase extraction can be improved. These new methods also focus on the semantics and context of a document, which is quite an improvement. Thanks to the introduction of keyphrase generation models, it's also possible to generate related keyphrases based on a given text document. This is useful, for example, when an author wants to make his work findable.
|
41 |
|
42 |
## π Model Description
|
43 |
This model is a fine-tuned KeyBART model on the Inspec dataset.
|
|
|
140 |
The model achieves the following results on the Inspec test set:
|
141 |
|
142 |
|
143 |
+
### Extractive keyphrases
|
144 |
|
145 |
| Dataset | P@5 | R@5 | F1@5 | P@10 | R@10 | F1@10 | P@M | R@M | F1@M | P@O | R@O | F1@O |
|
146 |
|:-----------------:|:----:|:----:|:----:|:----:|:----:|:-----:|:----:|:----:|:----:|:----:|:----:|:----:|
|
147 |
| Inspec Test Set | 0.40 | 0.37 | 0.35 | 0.20 | 0.37 | 0.24 | 0.42 | 0.37 | 0.36 | 0.33 | 0.33 | 0.33 |
|
148 |
|
149 |
+
### Abstractive keyphrases
|
150 |
|
151 |
| Dataset | P@5 | R@5 | F1@5 | P@10 | R@10 | F1@10 | P@M | R@M | F1@M | P@O | R@O | F1@O |
|
152 |
|:-----------------:|:----:|:----:|:----:|:----:|:----:|:-----:|:----:|:----:|:----:|:----:|:----:|:----:|
|