nipunsadvilkar commited on
Commit
4df6b08
·
1 Parent(s): e61e414

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -4,11 +4,12 @@ This model was fine-tuned using [Marathi RoBERTa](https://huggingface.co/flax-co
4
  ## Dataset
5
  IndicNLP Marathi news dataset consists 3 classes - `['lifestyle', 'entertainment', 'sports']` - with following docs distribution as per classes:
6
 
 
7
  | train | eval | test |
8
  | ----- | ---- | ---- |
9
  | 9672 | 477 | 478 |
10
 
11
- 💯 Our Marathi RoBERTa **`roberta-base-mr`** model outperformed both classifier mentioned in [Arora, G. (2020). iNLTK](https://www.semanticscholar.org/paper/iNLTK%3A-Natural-Language-Toolkit-for-Indic-Languages-Arora/5039ed9e100d3a1cbbc25a02c82f6ee181609e83/figure/3) and [Kunchukuttan, Anoop et al. AI4Bharat-IndicNLP.](https://www.semanticscholar.org/paper/AI4Bharat-IndicNLP-Corpus%3A-Monolingual-Corpora-and-Kunchukuttan-Kakwani/7997d432925aff0ba05497d2893c09918298ca55/figure/4)
12
 
13
  | Dataset | FT-W | FT-WC | INLP | iNLTK | **roberta-base-mr 🏆** |
14
  | --------------- | ----- | ----- | ----- | ----- | --------------------- |
 
4
  ## Dataset
5
  IndicNLP Marathi news dataset consists 3 classes - `['lifestyle', 'entertainment', 'sports']` - with following docs distribution as per classes:
6
 
7
+
8
  | train | eval | test |
9
  | ----- | ---- | ---- |
10
  | 9672 | 477 | 478 |
11
 
12
+ 💯 Our **`mr-indicnlp-classifier`** model fine tuned from **roberta-base-mr** Pretrained Marathi RoBERTa model outperformed both classifier mentioned in [Arora, G. (2020). iNLTK](https://www.semanticscholar.org/paper/iNLTK%3A-Natural-Language-Toolkit-for-Indic-Languages-Arora/5039ed9e100d3a1cbbc25a02c82f6ee181609e83/figure/3) and [Kunchukuttan, Anoop et al. AI4Bharat-IndicNLP.](https://www.semanticscholar.org/paper/AI4Bharat-IndicNLP-Corpus%3A-Monolingual-Corpora-and-Kunchukuttan-Kakwani/7997d432925aff0ba05497d2893c09918298ca55/figure/4)
13
 
14
  | Dataset | FT-W | FT-WC | INLP | iNLTK | **roberta-base-mr 🏆** |
15
  | --------------- | ----- | ----- | ----- | ----- | --------------------- |