lorenzoscottb
commited on
Commit
•
454b746
1
Parent(s):
1923380
Update README.md
Browse files
README.md
CHANGED
@@ -22,22 +22,16 @@ should probably proofread and complete it, then remove this comment. -->
|
|
22 |
|
23 |
# t5-base-DreamBank-Generation-Act-Char
|
24 |
|
25 |
-
This model is a fine-tuned version of [DReAMy-lib/t5-base-DreamBank-Generation-NER-Char](https://huggingface.co/DReAMy-lib/t5-base-DreamBank-Generation-NER-Char) on the
|
26 |
-
|
27 |
-
|
28 |
-
- Rouge1: 0.4708
|
29 |
-
- Rouge2: 0.4040
|
30 |
-
- Rougel: 0.4576
|
31 |
-
- Rougelsum: 0.4572
|
32 |
|
33 |
## Model description
|
34 |
|
35 |
-
## Training procedure
|
36 |
-
|
37 |
The model is trained end-to-end using a text2text solution to annotate dream reports following the Activity feature
|
38 |
from the Hall and Van de Castle scoring framework. Given a report, the model generates texts of the form
|
39 |
`[(initialiser : activity type : receiver)]`. For those cases where `initialiser` and `receiver` are the same
|
40 |
-
entity, the output will follow the `[(initialiser : alone : none)]` setting.
|
41 |
|
42 |
## Training procedure
|
43 |
|
|
|
22 |
|
23 |
# t5-base-DreamBank-Generation-Act-Char
|
24 |
|
25 |
+
This model is a fine-tuned version of [DReAMy-lib/t5-base-DreamBank-Generation-NER-Char](https://huggingface.co/DReAMy-lib/t5-base-DreamBank-Generation-NER-Char) on the DreamBank dataset.
|
26 |
+
The uploaded model contains the weights of the best-performing model (see table below), tune to annotate a given
|
27 |
+
dream report according to [Hall and Van de Castle the Activity feature](https://dreams.ucsc.edu/Coding/activities.html)
|
|
|
|
|
|
|
|
|
28 |
|
29 |
## Model description
|
30 |
|
|
|
|
|
31 |
The model is trained end-to-end using a text2text solution to annotate dream reports following the Activity feature
|
32 |
from the Hall and Van de Castle scoring framework. Given a report, the model generates texts of the form
|
33 |
`[(initialiser : activity type : receiver)]`. For those cases where `initialiser` and `receiver` are the same
|
34 |
+
entity, the output will follow the `[(initialiser : alone activity type : none)]` setting.
|
35 |
|
36 |
## Training procedure
|
37 |
|