makitanikaze
commited on
Commit
·
1291bbb
1
Parent(s):
266ffb2
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
|
6 |
+
tags:
|
7 |
+
- sequential-recommendation
|
8 |
+
- direct-recommendation
|
9 |
+
- explanation-generation
|
10 |
+
- text2text-generation
|
11 |
+
|
12 |
+
license: mit
|
13 |
+
|
14 |
+
datasets:
|
15 |
+
- amazon_us_reviews
|
16 |
+
|
17 |
+
metrics:
|
18 |
+
- NDCG
|
19 |
+
- HR
|
20 |
+
- MAE
|
21 |
+
- BLUE
|
22 |
+
- ROUGE
|
23 |
+
|
24 |
+
widget:
|
25 |
+
- text: "I find the purchase history list of user_823 : \n 5255 -> 3001 -> 3771 -> 2973 \n I wonder what is the next item to recommend to the user . Can you help me decide ?"
|
26 |
+
example_title: "Sequential Recommendation"
|
27 |
+
- text: "Pick the most suitable item from the following list and recommend to user_182 : \n 5871 , 3575 , 6355 , 3665 , 7968 , 1054 , 11837 , 9031 , 2643 , 3125 , 11476 , 1529 , 6300 , 11755 , 9410 , 1578 , 5953 , 5042 , 10881 , 2221 , 11286 , 10458 , 2081 , 3722 , 10581 , 5879 , 1780 , 7411 , 5202 , 2082 , 82 , 8131 , 77 , 8097 , 1053 , 9946 , 1341 , 4508 , 2613 , 629 , 4869 , 9833 , 7076 , 6178 , 6679 , 6650 , 472 , 8821 , 4005 , 4184 , 2866 , 4988 , 10759 , 6358 , 4137 , 790 , 5390 , 9330 , 3691 , 2667 , 5620 , 11982 , 4799 , 10062 , 4278 , 4530 , 7944 , 10225 , 1766 , 6657 , 11371 , 305 , 1091 , 7144 , 1869 , 744 , 295 , 91 , 6947 , 9290 , 2977 , 11206 , 1677 , 7812 , 1159 , 1128 , 8762 , 5795 , 8061 , 9639 , 6161 , 2142 , 8124 , 5316 , 10425 , 12097 , 476 , 5710 , 1802 , 8969"
|
28 |
+
example_title: "Direct Recommendation"
|
29 |
+
- text: "Based on the feature word shampoo , generate an explanation for user_837 about this product : Dove Nourishing Oil Shampoo, 25.4 Ounce"
|
30 |
+
example_title: "Explanation Generation"
|
31 |
+
---
|
32 |
+
|
33 |
+
# P5 (Beauty Base)
|
34 |
+
Recommendation as Language Processing: A Unified Pretrain, Personalized Prompt & Predict Paradigm
|
35 |
+
|
36 |
+
![model image](https://raw.githubusercontent.com/jeykigung/P5/main/pic/teaser.png)
|