---
language: 
  - en

tags:
- sequential-recommendation
- direct-recommendation
- explanation-generation
- text2text-generation
  
license: mit

datasets:
- yelp_review_full

metrics:
- NDCG
- HR
- MAE
- BLUE
- ROUGE

widget:
- text: "Based on the visit history of Herman : \n 236 -> 4979 -> 3240 -> 2208 -> 168 -> 12101 \n Can you decide the next business likely to be visited by the user ?"
  example_title: "Sequential Recommendation"
- text: "We want to make recommendation for user_1618 .  Select the best item from these candidates : \n 13978 , 2053 , 19198 , 16484 , 771 , 5354 , 10803 , 18199 , 15098 , 1070 , 7183 , 193 , 13633 , 16465 , 1302 , 14943 , 12902 , 10984 , 18198 , 6062 , 11955 , 6809 , 12601 , 2373 , 14706 , 8889 , 17980 , 17294 , 15002 , 12237 , 13299 , 18856 , 7066 , 11792 , 17093 , 18779 , 19563 , 2615 , 17865 , 11774 , 13562 , 11128 , 14810 , 10149 , 18543 , 12854 , 12508 , 7662 , 7227 , 3058 , 11704 , 1200 , 12439 , 17873 , 16280 , 15225 , 307 , 11428 , 17107 , 4727 , 2030 , 6914 , 8234 , 2174 , 14340 , 17577 , 15342 , 14741 , 19058 , 14694 , 2114 , 15739 , 8739 , 14263 , 4687 , 4977 , 6685 , 381 , 16542 , 19230 , 9977 , 8449 , 18537 , 6616 , 8945 , 12265 , 4836 , 7705 , 19865 , 15843 , 18715 , 12834 , 18955 , 6324 , 4740 , 14717 , 2752 , 2131 , 5957 , 7511"
  example_title: "Direct Recommendation"
- text: "Based on the feature word drinks , generate an explanation for user_5657 about this business : Ghost Ranch: Modern Southwest Cuisine"
  example_title: "Explanation Generation"
---

# P5 (Yelp Small)
Recommendation as Language Processing: A Unified Pretrain, Personalized Prompt & Predict Paradigm 

![model image](https://raw.githubusercontent.com/jeykigung/P5/main/pic/teaser.png)