fragata commited on
Commit
a433ceb
1 Parent(s): c969d77

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +45 -0
README.md ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+
3
+ language:
4
+ - hu
5
+ tags:
6
+ - text-classification
7
+ license: gpl
8
+ metrics:
9
+ - accuracy
10
+ widget:
11
+ - text: "Jó reggelt! majd küldöm az élményhozókat:)."
12
+
13
+ ---
14
+
15
+ # Hungarian Sentence-level Sentiment Analysis model with huBERT
16
+
17
+ - Pretrained model used: huBERT
18
+ - Finetuned on Hungarian Twitter Sentiment (HTS) Corpus
19
+
20
+ ## Limitations
21
+
22
+ - max_seq_length = 128
23
+
24
+ ## Results
25
+
26
+ | Model | HTS2 | HTS5 |
27
+ | ------------- | ------------- | ------------- |
28
+ | huBERT | **85.55** | 68.99 |
29
+ | XLM-RoBERTa| 85.56 | 85.56 |
30
+
31
+ ## Citation
32
+ If you use this model, please cite the following paper:
33
+
34
+ ```
35
+ @inproceedings {yang-bart,
36
+ title = {Improving Performance of Sentence-level Sentiment Analysis with Data Augmentation Methods},
37
+ booktitle = {Proceedings of 12th IEEE International Conference on Cognitive Infocommunications (CogInfoCom 2021)},
38
+ year = {2021},
39
+ publisher = {IEEE},
40
+ address = {Online},
41
+ author = {{Laki, László and Yang, Zijian Győző}}
42
+ pages = {417--422}
43
+ }
44
+
45
+ ```