English
Summarization
5 papers
igorgavi commited on
Commit
e95a62e
1 Parent(s): 722f2b5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -11
README.md CHANGED
@@ -207,20 +207,28 @@ summary often written by its very author.
207
  ## Evaluation results
208
 
209
  Each of the datasets' documents was summarized through every summarization method applied in the code and evaluated
210
- in comparison with the gold-standard summaries.
 
211
 
212
- Table 2: Results from Pre-trained Longformer + ML models.
 
 
213
 
214
- | ML Model | Accuracy | F1 Score | Precision | Recall |
215
- || tentativa ||||
216
- |:--------:|:--------:|:--------:|||
217
- |:--------:|:---------:|:---------:|:---------:|:---------:|
218
- | NN | 0.8269 | 0.8754 |0.7950 | 0.9773 |
219
- | DNN | 0.8462 | 0.8776 |0.8474 | 0.9123 |
220
- | CNN | 0.8462 | 0.8776 |0.8474 | 0.9123 |
221
- | LSTM | 0.8269 | 0.8801 |0.8571 | 0.9091 |
222
 
223
- ![TESTE](https://huggingface.co/unb-lamfo-nlp-mcti/NLP-ATS-MCTI/resolve/main/tabela-arxiv.png)
 
 
 
 
 
 
 
 
 
 
224
 
225
  ## Checkpoints
226
  - Examples
 
207
  ## Evaluation results
208
 
209
  Each of the datasets' documents was summarized through every summarization method applied in the code and evaluated
210
+ in comparison with the gold-standard summaries. The following tables provide the results for many evaluation methods applied
211
+ to the many datasets:
212
 
213
+ Table 1: Scientific Papers (arXiv + PubMed) results
214
+ ![arxiv1](hhttps://huggingface.co/unb-lamfo-nlp-mcti/NLP-ATS-MCTI/resolve/main/tabela-arxiv-1.png)
215
+ ![arxiv2](hhttps://huggingface.co/unb-lamfo-nlp-mcti/NLP-ATS-MCTI/resolve/main/tabela-arxiv-2.png)
216
 
217
+ Table 2: BIGPATENT results
218
+ ![bigpatent1](hhttps://huggingface.co/unb-lamfo-nlp-mcti/NLP-ATS-MCTI/resolve/main/tabela-bigpatent-1.png)
219
+ ![bigpatent2](hhttps://huggingface.co/unb-lamfo-nlp-mcti/NLP-ATS-MCTI/resolve/main/tabela-bigpatent-2.png)
 
 
 
 
 
220
 
221
+ Table 3: CNN Corpus results
222
+ ![cnncorpus1](hhttps://huggingface.co/unb-lamfo-nlp-mcti/NLP-ATS-MCTI/resolve/main/tabela-cnncorpus-2.png)
223
+ ![cnncorpus2](hhttps://huggingface.co/unb-lamfo-nlp-mcti/NLP-ATS-MCTI/resolve/main/tabela-cnncorpus-2.png)
224
+
225
+ Table 4: CNN + Daily Mail results
226
+ ![cnndm1](hhttps://huggingface.co/unb-lamfo-nlp-mcti/NLP-ATS-MCTI/resolve/main/tabela-cnn-dailymail-1.png)
227
+ ![cnndm2](hhttps://huggingface.co/unb-lamfo-nlp-mcti/NLP-ATS-MCTI/resolve/main/tabela-cnn-dailymail-2.png)
228
+
229
+ Table 5: XSum results
230
+ ![xsum1](hhttps://huggingface.co/unb-lamfo-nlp-mcti/NLP-ATS-MCTI/resolve/main/tabela-xsum-1.png)
231
+ ![xsum2](hhttps://huggingface.co/unb-lamfo-nlp-mcti/NLP-ATS-MCTI/resolve/main/tabela-xsum-2.png)
232
 
233
  ## Checkpoints
234
  - Examples