Update README.md
Browse files
README.md
CHANGED
|
@@ -1,18 +1,19 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: cc-by-sa-4.0
|
| 3 |
-
datasets:
|
| 4 |
-
- GiliGold/VAD_KnessetCorpus
|
| 5 |
-
- HaifaCLGroup/KnessetCorpus
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
-
|
| 11 |
-
-
|
| 12 |
-
-
|
| 13 |
-
-
|
| 14 |
-
-
|
| 15 |
-
|
|
|
|
| 16 |
# VAD Binomial Regression Models
|
| 17 |
This repository contains three binomial regression models designed to predict VAD (Valence, Arousal, Dominance) scores for text inputs.
|
| 18 |
Each model is stored as a separate pickle (.pkl) file:
|
|
@@ -28,9 +29,9 @@ Before making predictions, input text must be converted into embeddings using th
|
|
| 28 |
## Training Data
|
| 29 |
The models were trained using a combination of datasets to ensure robust and generalizable predictions:
|
| 30 |
|
| 31 |
-
Hebrew version of the [Emobank Dataset](https://aclanthology.org/E17-2092/) (by buechel-hahn-2017-emobank): A comprehensive dataset containing emotional text data that we automaticaly translated to Hebrew using [Google/madlad400-3b-mt](https://huggingface.co/google/madlad400-3b-mt).
|
| 32 |
-
[Hebrew VAD Lexicon](https://huggingface.co/datasets/GiliGold/Hebrew_VAD_lexicon): A lexicon that provides VAD scores for Hebrew words.
|
| 33 |
-
[Knesset Sentences](https://huggingface.co/datasets/GiliGold/VAD_KnessetCorpus): A manually annotated set of 120 Knesset sentences with VAD scores, serving as an additional benchmark and source of training data.
|
| 34 |
This diverse training data allowed the models to capture nuanced emotional features across different text domains, especially in Hebrew.
|
| 35 |
|
| 36 |
## Model Details
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-sa-4.0
|
| 3 |
+
datasets:
|
| 4 |
+
- GiliGold/VAD_KnessetCorpus
|
| 5 |
+
- HaifaCLGroup/KnessetCorpus
|
| 6 |
+
- GiliGold/Hebrew_VAD_lexicon
|
| 7 |
+
language:
|
| 8 |
+
- he
|
| 9 |
+
tags:
|
| 10 |
+
- vad
|
| 11 |
+
- valence
|
| 12 |
+
- arousal
|
| 13 |
+
- dominance
|
| 14 |
+
- regression
|
| 15 |
+
- knesset
|
| 16 |
+
---
|
| 17 |
# VAD Binomial Regression Models
|
| 18 |
This repository contains three binomial regression models designed to predict VAD (Valence, Arousal, Dominance) scores for text inputs.
|
| 19 |
Each model is stored as a separate pickle (.pkl) file:
|
|
|
|
| 29 |
## Training Data
|
| 30 |
The models were trained using a combination of datasets to ensure robust and generalizable predictions:
|
| 31 |
|
| 32 |
+
- A Hebrew version of the [Emobank Dataset](https://aclanthology.org/E17-2092/) (by buechel-hahn-2017-emobank): A comprehensive dataset containing emotional text data that we automaticaly translated to Hebrew using [Google/madlad400-3b-mt](https://huggingface.co/google/madlad400-3b-mt).
|
| 33 |
+
- [Hebrew VAD Lexicon](https://huggingface.co/datasets/GiliGold/Hebrew_VAD_lexicon): A lexicon that provides VAD scores for Hebrew words.
|
| 34 |
+
- [Knesset Sentences](https://huggingface.co/datasets/GiliGold/VAD_KnessetCorpus): A manually annotated set of 120 Knesset sentences with VAD scores, serving as an additional benchmark and source of training data.
|
| 35 |
This diverse training data allowed the models to capture nuanced emotional features across different text domains, especially in Hebrew.
|
| 36 |
|
| 37 |
## Model Details
|