--- language: - en tags: - sequential-recommendation - direct-recommendation - explanation-generation - text2text-generation license: mit datasets: - amazon_us_reviews metrics: - NDCG - HR - MAE - BLUE - ROUGE widget: - text: "Here is the purchase history list of user_508 : \n 4162 , 816 , 3770 , 756 , 4163 \n try to recommend next item to the user" example_title: "Sequential Recommendation" - text: "We want to make recommendation for user_497 . Select the best item from these candidates : \n 7553 , 10601 , 611 , 5844 , 14863 , 18162 , 16144 , 16003 , 11096 , 5846 , 4406 , 6849 , 17650 , 13302 , 13240 , 6132 , 4620 , 847 , 7341 , 5845 , 10557 , 12080 , 13872 , 10953 , 4230 , 9146 , 17930 , 14731 , 16458 , 1735 , 6347 , 11951 , 17576 , 14745 , 9038 , 8915 , 8311 , 10365 , 4663 , 6396 , 1900 , 1456 , 12718 , 4222 , 9399 , 8517 , 11528 , 16162 , 598 , 2064 , 1417 , 625 , 14553 , 6535 , 13867 , 5587 , 13231 , 9123 , 5654 , 11651 , 8039 , 2903 , 1178 , 9587 , 4161 , 748 , 18270 , 15012 , 13111 , 4802 , 8200 , 17202 , 7991 , 17123 , 3650 , 2639 , 4071 , 16999 , 10604 , 3212 , 7766 , 7414 , 12460 , 17144 , 10218 , 2784 , 4857 , 17745 , 12748 , 5513 , 4637 , 729 , 17925 , 17573 , 4939 , 2451 , 15202 , 9694 , 11253 , 17445" example_title: "Direct Recommendation" - text: "Based on the feature word sweater , generate an explanation for user_4479 about this product : Fobus Standard Holster RH Paddle GL4 Glock 29/30/39/ 21SF/30SF / S&W 99 / S&W Sigma Series V" example_title: "Explanation Generation" --- # P5 (Sports Small) Recommendation as Language Processing: A Unified Pretrain, Personalized Prompt & Predict Paradigm ![model image](https://raw.githubusercontent.com/jeykigung/P5/main/pic/teaser.png)