Commit
•
4f3726a
1
Parent(s):
9dfb86d
Update
Browse files
README.md
CHANGED
@@ -1,25 +1,32 @@
|
|
1 |
---
|
2 |
-
license: mit
|
3 |
language:
|
4 |
- de
|
5 |
tags:
|
6 |
- text-classication
|
|
|
7 |
metrics:
|
8 |
- precision
|
|
|
|
|
9 |
widget:
|
10 |
-
- text: "
|
11 |
-
example_classification: "Enthält Ansprache an Redaktion"
|
12 |
---
|
13 |
|
14 |
-
#
|
|
|
|
|
|
|
|
|
15 |
|
16 |
This is a model for the task of classifying whether or not a articles comment addresses the moderation team/authors of the media house that published the article. In this prototype stage the media houses are Bayerischer Rundfunk and Mitteldeutscher Rundfunk.
|
17 |
|
18 |
This classification task is implemented as a binary classification into:
|
19 |
|
20 |
-
|
21 |
-
|
|
|
|
|
|
|
22 |
|
23 |
-
|
24 |
|
25 |
-
**Our finetuned model is still work in progress. More information to come.**
|
|
|
1 |
---
|
|
|
2 |
language:
|
3 |
- de
|
4 |
tags:
|
5 |
- text-classication
|
6 |
+
license: mit
|
7 |
metrics:
|
8 |
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
widget:
|
12 |
+
- text: "Im Artikel wird leider nicht erwähnt, inwieweit und ob dadurch Natur zerstört werden muss."
|
|
|
13 |
---
|
14 |
|
15 |
+
# German news title gen
|
16 |
+
|
17 |
+
Please node that this model originates from the ["What's there, what's missing"](https://interaktiv.br.de/ai-detect-newsroom-mentions-in-comments/) collaboration of [AI & Automation Labl of Bayerischer Rundfunk](https://www.br.de/extra/ai-automation-lab/index.html) and [Mitteldeutscher Rundfunk](https://www.mdr.de/) as well as [ida](https://idalab.de/). The collaboration took place during the [JournalismAI fellowship '22](https://www.lse.ac.uk/media-and-communications/polis/JournalismAI/Fellowship-Programme). The model presented is part of the the documenation of the half year of project time. The related technical framework can be found a [github](https://github.com/br-data/wtwm-topic-modelling).
|
18 |
+
|
19 |
+
## The task
|
20 |
|
21 |
This is a model for the task of classifying whether or not a articles comment addresses the moderation team/authors of the media house that published the article. In this prototype stage the media houses are Bayerischer Rundfunk and Mitteldeutscher Rundfunk.
|
22 |
|
23 |
This classification task is implemented as a binary classification into:
|
24 |
|
25 |
+
label 0: the comment holds no mention
|
26 |
+
|
27 |
+
label 1: the comment addresses the moderation team/authors of the media house
|
28 |
+
|
29 |
+
We decided to use [german-gpt2](https://huggingface.co/dbmdz/german-gpt2) by MDZ of Bayerische Staatsbibliothek as the foundation model.
|
30 |
|
31 |
+
**This model is still work in progress and might be updated in the future.**
|
32 |
|
|