Update README.md

README.md

@@ -18,7 +18,19 @@ should probably proofread and complete it, then remove this comment. -->
 # t5_recommendation_sports_equipment_english
 
 This model is a fine-tuned version of [t5-large](https://huggingface.co/t5-large) on a custom dataset, consisting of sports equipment customers have purchased, and items to recommended next.
-It achieves the following results on the evaluation set:
+
+This is based on the paper ["Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)"](https://arxiv.org/pdf/2203.13366.pdf), where the researchers use a language model as a recommendation system.
+- LLMs can "understand" relationships between words/terms via embeddings produced by the transformer architecture. This allows for relationships to be taken into account.
+- By feeding an LLM a history of items purchased as the input and the next item purchased as the output, the model can learn what to recommend based on the semantics of the product's name.
+  - Taking multiple examples of different users' purchase history into account, the LLM can also learn what genres of products go with what.
+  - This essentially replicates collaboritve filtering
+- Benefits include:
+  - Getting past the cold-start problem with ease (when new items are introduced, the model will be able to understand what's similar to it from the name alone).
+  - Avoiding tedious, manual feature engineering (using natural language, the LLM will automatically learn).
+ 
+The github repository for fine-tuning this model can be viewed [here](https://github.com/Mohammadhia/t5_p5_recommendation_system).
+
+The fine-tuned T5 model achieves the following results on the evaluation set:
 - Loss: 0.4554
 - Rouge1: 57.1429
 - Rouge2: 47.6190
@@ -28,18 +40,24 @@ It achieves the following results on the evaluation set:
 
 ## Model description
 
-More information needed
+T5 is an open-source sequence-to-sequence model released by Google in 2020, from which several variants have been developed. This fine-tuned version is an attempt to replicate what was presented in the [P5 paper](https://arxiv.org/pdf/2203.13366.pdf), with a custom dataset (based on sports equipment).
+
+More about this model (T5) can be viewed [here](https://huggingface.co/docs/transformers/model_doc/t5).
+
+The P5 models from the paper can be viewed on the [Hugging Face Hub](https://huggingface.co/makitanikaze/P5) as well as in this [repository](https://github.com/jeykigung/P5).
 
 ## Intended uses & limitations
 
-More information needed
+Can be used as you please, but is limited to the sports equipment dataset it was fine-tuned on. Your mileage may vary.
 
 ## Training and evaluation data
 
-More information needed
+Please see this [repository](https://github.com/Mohammadhia/t5_p5_recommendation_system) for training and evaluation data.
 
 ## Training procedure
 
+Please see this [repository](https://github.com/Mohammadhia/t5_p5_recommendation_system) for training and evaluation data.
+
 ### Training hyperparameters
 
 The following hyperparameters were used during training: