Tahmid commited on
Commit
c426dea
1 Parent(s): 588ad14

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -0
README.md CHANGED
@@ -36,6 +36,27 @@ print("\n" + "-" * 50)
36
  print("\n" + "-" * 50)
37
  ```
38
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  ## Citation
40
 
41
  If you use this model, please cite the following paper:
 
36
  print("\n" + "-" * 50)
37
  ```
38
 
39
+ ## Benchmarks
40
+
41
+ | | SC | EC | DC | NER | NLI |
42
+ |-------------|--------|-------|-------|----------|----------|
43
+ |`Metrics` | `Accuracy` | `F1*` | `Accuracy` | `F1 (Entity)*` | `Accuracy` |
44
+ |[mBERT](https://huggingface.co/bert-base-multilingual-cased) | 83.39 | 56.02 | 98.64 | 67.40 | 75.40 |
45
+ |[XLM-R](https://huggingface.co/xlm-roberta-base) | 89.49 | 66.70 | 98.71 | 70.63 | 76.87 |
46
+ |[sagorsarker/bangla-bert-base](https://huggingface.co/sagorsarker/bangla-bert-base) | 87.30 | 61.51 | 98.79 | 70.97 | 70.48 |
47
+ [monsoon-nlp/bangla-electra](https://huggingface.co/monsoon-nlp/bangla-electra) | 73.54 | 34.55 | 97.64 | 52.57 | 63.48 |
48
+ |***BanglaBERT*** | **92.18** | **74.27** | **99.07** | **72.18** | **82.94**|
49
+
50
+ `*` - Weighted Average
51
+
52
+ The benchmarking datasets are as follows:
53
+ * **SC:** **[Sentiment Classification](https://ieeexplore.ieee.org/document/8554396/)**
54
+ * **EC:** **[Emotion Classification](https://aclanthology.org/2021.naacl-srw.19/)**
55
+ * **DC:** **[Document Classification](https://arxiv.org/abs/2005.00085)**
56
+ * **NER:** **[Named Entity Recognition](https://content.iospress.com/articles/journal-of-intelligent-and-fuzzy-systems/ifs179349)**
57
+ * **NLI:** **[Natural Language Inference](#datasets)**
58
+
59
+
60
  ## Citation
61
 
62
  If you use this model, please cite the following paper: