sijunhe commited on
Commit
12c1b68
1 Parent(s): db25ecc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +46 -1
README.md CHANGED
@@ -1,4 +1,49 @@
1
  ---
2
  library_name: paddlenlp
 
 
 
3
  ---
4
- # PaddlePaddle/uie-senta-micro
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  library_name: paddlenlp
3
+ license: apache-2.0
4
+ language:
5
+ - zh
6
  ---
7
+ [![paddlenlp-banner](https://user-images.githubusercontent.com/1371212/175816733-8ec25eb0-9af3-4380-9218-27c154518258.png)](https://github.com/PaddlePaddle/PaddleNLP)
8
+
9
+ # PaddlePaddle/uie-senta-base
10
+
11
+ Sentiment analysis is a research hotspot in recent years, aiming at analyzing, processing, summarizing and reasoning emotionally subjective texts. Sentiment analysis has a wide range of application scenarios and can be applied to consumer decision making, public opinion mining, personalized recommendation and so on.
12
+
13
+ According to the analysis granularity, it can be roughly divided into three categories: document-level sentiment analysis, sentence-level sentiment analysis and aspect-level sentiment analysis. Among them, aspect-level sentiment analysis includes multiple subtasks, such as aspect term extraction, opinion term extraction, aspect-opinion-sentiment triplet extraction, etc.
14
+
15
+
16
+ UIE-Senta is a type of Chinese sentiment analysis model, which uses UIE as backbone and further trained based on large amount of samples related to sentiment analysis. So it has a stronger ability to understand sentiment knowledge and handle the related samples. Currently, UIE-Senta supports most of basic sentiment analysis capabilities, including sentiment-level sentiment classification, aspect-term extraction, opinion-term extraction, aspect-sentiment pair extraction, aspect-opinion pair extraction, aspect-opinion-sentiment triple extraction. You could perform sentiment analysis with UIE-Senta to improve your business analysis capabilities.
17
+
18
+
19
+ <div align="center">
20
+ <img src="https://user-images.githubusercontent.com/35913314/199965793-f0933baa-5b82-47da-9271-ba36642119f8.png" />
21
+ </div>
22
+
23
+
24
+ ## Available Models
25
+
26
+ | Model Name | Model Config |
27
+ | :---------------: | :-----------------------------: |
28
+ | `uie-senta-base` | 12-layers, 768-hidden, 12-heads |
29
+ | `uie-senta-medium` | 6-layers, 768-hidden, 12-heads |
30
+ | `uie-senta-mini` | 6-layers, 384-hidden, 12-heads |
31
+ | `uie-senta-micro` | 4-layers, 384-hidden, 12-heads |
32
+ | `uie-senta-nano` | 4-layers, 312-hidden, 12-heads |
33
+
34
+
35
+ ## Performance on Text Dataset
36
+
37
+ We conducted experiments to compare the performance different Models based on a in-house test set, which containing samples from multiple fields, such as hotel, restaurant,clothes and so. The comparison results are as follows.
38
+
39
+ | Model Name | Precision | Recall | F1 |
40
+ | :----------------: | :--------: | :--------: | :--------: |
41
+ | `uie-senta-base` | 0.93403 | 0.92795 | 0.93098 |
42
+ | `uie-senta-medium` | 0.93146 | 0.92137 | 0.92639 |
43
+ | `uie-senta-mini` | 0.91799 | 0.92028 | 0.91913 |
44
+ | `uie-senta-micro` | 0.91542 | 0.90957 | 0.91248 |
45
+ | `uie-senta-nano` | 0.90817 | 0.90878 | 0.90847 |
46
+
47
+
48
+ > Detailed Info: https://github.com/1649759610/PaddleNLP/tree/develop/applications/sentiment_analysis/unified_sentiment_extraction
49
+