DeDeckerThomas commited on
Commit
31531b7
β€’
1 Parent(s): 0855882

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -9
README.md CHANGED
@@ -54,7 +54,6 @@ from transformers import (
54
  AutoModelForSeq2SeqLM,
55
  AutoTokenizer,
56
  )
57
- import numpy as np
58
 
59
 
60
  class KeyphraseGenerationPipeline(Text2TextGenerationPipeline):
@@ -71,22 +70,24 @@ class KeyphraseGenerationPipeline(Text2TextGenerationPipeline):
71
  results = super().postprocess(
72
  model_outputs=model_outputs
73
  )
74
- return [[keyphrase.strip() for keyphrase in result.get("generated_text").split(self.keyphrase_sep_token)] for result in results]
 
75
  ```
76
 
77
  ```python
78
  # Load pipeline
79
- model_name = "DeDeckerThomas/keyphrase-generation-t5-small-openkp"
80
  generator = KeyphraseGenerationPipeline(model=model_name)
81
 
82
  ```python
83
  text = """
84
  Keyphrase extraction is a technique in text analysis where you extract the important keyphrases from a text.
85
  Since this is a time-consuming process, Artificial Intelligence is used to automate it.
86
- Currently, classical machine learning methods, that use statistics and linguistics, are widely used for the extraction process.
87
- The fact that these methods have been widely used in the community has the advantage that there are many easy-to-use libraries.
88
- Now with the recent innovations in deep learning methods (such as recurrent neural networks and transformers, GANS, …), keyphrase extraction can be improved.
89
- These new methods also focus on the semantics and context of a document, which is quite an improvement.
 
90
  """.replace(
91
  "\n", ""
92
  )
@@ -99,7 +100,7 @@ print(keyphrases)
99
 
100
  ```
101
  # Output
102
- [['keyphrase extraction', 'text analysis', 'artificial intelligence', 'classical machine learning', 'statistics']]
103
  ```
104
 
105
  ## πŸ“š Training Dataset
@@ -200,4 +201,4 @@ Abstractive keyphrases
200
  For more information on the evaluation process, you can take a look at the keyphrase extraction evaluation notebook.
201
 
202
  ## 🚨 Issues
203
- Please feel free to contact Thomas De Decker for any problems with this model.
 
54
  AutoModelForSeq2SeqLM,
55
  AutoTokenizer,
56
  )
 
57
 
58
 
59
  class KeyphraseGenerationPipeline(Text2TextGenerationPipeline):
 
70
  results = super().postprocess(
71
  model_outputs=model_outputs
72
  )
73
+ return [[keyphrase.strip() for keyphrase in result.get("generated_text").split(self.keyphrase_sep_token) if keyphrase != ""] for result in results]
74
+
75
  ```
76
 
77
  ```python
78
  # Load pipeline
79
+ model_name = "ml6team/keyphrase-generation-t5-small-openkp"
80
  generator = KeyphraseGenerationPipeline(model=model_name)
81
 
82
  ```python
83
  text = """
84
  Keyphrase extraction is a technique in text analysis where you extract the important keyphrases from a text.
85
  Since this is a time-consuming process, Artificial Intelligence is used to automate it.
86
+ Currently, classical machine learning methods, that use statistics and linguistics,
87
+ are widely used for the extraction process. The fact that these methods have been widely used in the community
88
+ has the advantage that there are many easy-to-use libraries. Now with the recent innovations in NLP,
89
+ transformers can be used to improve keyphrase extraction. Transformers also focus on the semantics
90
+ and context of a document, which is quite an improvement.
91
  """.replace(
92
  "\n", ""
93
  )
 
100
 
101
  ```
102
  # Output
103
+ [['keyphrase extraction', 'text analysis', 'artificial intelligence']]
104
  ```
105
 
106
  ## πŸ“š Training Dataset
 
201
  For more information on the evaluation process, you can take a look at the keyphrase extraction evaluation notebook.
202
 
203
  ## 🚨 Issues
204
+ Please feel free to start discussions in the Community Tab.