Update README.md

README.md

@@ -1,14 +1,25 @@
-## facebook/tart-full-flan-t5-xl
+# Task-aware Retrieval with Instructions
 
-`facebook/tart-full-flan-t5-xl` is a multi-task cross-encoder model trained via instruction-tuning on approximately 40 retrieval tasks, initialized with [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl).
+Official repository: [github.com/facebookresearch/tart](https://github.com/facebookresearch/tart)
+
+### Model descriptions
+
+`facebook/tart-full-flan-t5-xl` is a multi-task cross-encoder model trained via instruction-tuning on approximately 40 retrieval tasks, which is initialized with [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl).
+
+TART-full is a 1.5 billion cross-necoder and it can rerank top documents given a query and natural language instruction (e.g., *find a Wikipedia paragraph that answers this question.*). 
+Experimental results on widely-used [BEIR](https://github.com/beir-cellar/beir), [LOTTE](https://huggingface.co/datasets/colbertv2/lotte), and our new evaluation, [X^2-Retrieval](https://github.com/facebookresearch/tart/cross_task_cross_eval) show that TART-full outperforms previous state-of-the-art methods by levaraging natural language instructions. 
+
+More details about modeling and training are in our paper: [Task-aware Retrieval with Instructions](https://arxiv.org/abs/2211.09260). 
 
 ### Installation
-```
+```sh
 git clone https://github.com/facebookresearch/tart
 pip install -r requirements.txt
 cd tart/TART
 ```
 
+### How to use?
+
 TART-full can be loaded through our customized EncT5 model. 
 ```python
 from src.modeling_enc_t5 import EncT5ForSequenceClassification
@@ -17,14 +28,14 @@ import torch
 import torch.nn.functional as F
 
 # load TART full and tokenizer
-model = EncT5ForSequenceClassification.from_pretrained("tart_full_flan_t5_xl")
-tokenizer =  EncT5Tokenizer.from_pretrained("tart_full_flan_t5_xl")
+model = EncT5ForSequenceClassification.from_pretrained("facebook/tart-full-flan-t5-xl")
+tokenizer =  EncT5Tokenizer.from_pretrained("facebook/tart-full-flan-t5-xl")
 model.eval()
 
 q = "What is the population of Tokyo?"
 in_answer = "retrieve a passage that answers this question from Wikipedia"
 
-p_1 = "The population of Japan's capital, Tokyo, dropped by about 48,600 people to just under 14 million at the start of 2022."
+p_1 = "The population of Japan's capital, Tokyo, dropped by about 48,600 people to just under 14 million at the start of 2022, the first decline since 1996, the metropolitan government reported Monday."
 p_2 = "Tokyo, officially the Tokyo Metropolis (東京都, Tōkyō-to), is the capital and largest city of Japan."
 
 # 1. TART-full can identify more relevant paragraph. 
@@ -32,7 +43,8 @@ features = tokenizer(['{0} [SEP] {1}'.format(in_answer, q), '{0} [SEP] {1}'.form
 with torch.no_grad():
     scores = model(**features).logits
     normalized_scores = [float(score[1]) for score in F.softmax(scores, dim=1)]
-print([p_1, p_2]np.argmax(normalized_scores)) # "The population of Japan's capital, Tokyo, dropped by about 48,600 people to just under 14 million."
+
+print([p_1, p_2][np.argmax(normalized_scores)]) # "The population of Japan's capital, Tokyo, dropped by about 48,600 people to just under 14 million ... "
 
 # 2. TART-full can identify the document that is more relevant AND follows instructions.
 in_sim = "You need to find duplicated questions in Wiki forum. Could you find a question that is similar to this question"
@@ -42,5 +54,5 @@ with torch.no_grad():
     scores = model(**features).logits
     normalized_scores = [float(score[1]) for score in F.softmax(scores, dim=1)]
 
-print([p, q_1]np.argmax(normalized_scores)) #  "How many people live in Tokyo?"
+print([p, q_1][np.argmax(normalized_scores)]) #  "How many people live in Tokyo?"
 ```