Update README.md
Browse files
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
2 |
language: en
|
3 |
tags:
|
4 |
-
-
|
5 |
license: apache-2.0
|
6 |
datasets:
|
7 |
- Opinosis
|
@@ -39,22 +39,21 @@ and English.
|
|
39 |
|
40 |
## Model description
|
41 |
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
bibendum cursus. Nunc volutpat vitae neque ut bibendum.
|
58 |
|
59 |
![architeru](https://github.com/marcosdib/S2Query/Classification_Architecture_model.png)
|
60 |
|
|
|
1 |
---
|
2 |
language: en
|
3 |
tags:
|
4 |
+
- Summarization
|
5 |
license: apache-2.0
|
6 |
datasets:
|
7 |
- Opinosis
|
|
|
39 |
|
40 |
## Model description
|
41 |
|
42 |
+
This Automatic Text Summarizarion (ATS) Model was developed to be applied to the Research Financing Products Portfolio (FPP)
|
43 |
+
of the Brazilian Ministry of Science, Technology and Innovation. It was produced in parallel with the writing of a Sistematic
|
44 |
+
Literature Review paper, in which there is a discussion concerning many summarization methods, datasets, and evaluators as well
|
45 |
+
as a brief overview of the nature of the task itself and the state-of-the-art of its implementation.
|
46 |
+
|
47 |
+
The input of the model can be either a single text or a csv file containing multiple texts (in the English language) and its output are the summarized texts
|
48 |
+
and their evaluation metrics. As an optional (although recommended) input, the model accepts gold-standard summaries for the texts,
|
49 |
+
i.e., human written (or extracted) summaries of the texts which are considered to be good representations of their contents. Evaluators
|
50 |
+
like ROUGE, which in its many variations is the most used to perform the task, require gold-standard summaries as inputs. There are, however,
|
51 |
+
Evaluation Methods which do not deppend on the existence of a golden-summary (e.g. the cosine similarity method, the Kullback Leibler Divergence method)
|
52 |
+
and this is why an evaluation can be made even when only the text is taken as an input to the model.
|
53 |
+
|
54 |
+
|
55 |
+
|
56 |
+
|
|
|
57 |
|
58 |
![architeru](https://github.com/marcosdib/S2Query/Classification_Architecture_model.png)
|
59 |
|