Update README.md

README.md

@@ -13,9 +13,18 @@ metrics:
 ---
 
 # Naive Listwise MonoBERT trained on Baidu-ULTR
-A flax-based MonoBERT cross encoder trained on the Baidu-ULTR dataset with a **listwise softmax cross-entropy loss on clicks**. The loss is called "naive" as we use user clicks as a signal of relevance without any additional position bias correction. For more info, read our paper here.
+A flax-based MonoBERT cross encoder trained on the [Baidu-ULTR](https://arxiv.org/abs/2207.03051) dataset with a **listwise softmax cross-entropy loss on clicks**. The loss is called "naive" as we use user clicks as a signal of relevance without any additional position bias correction. For more info, [read our paper here](https://arxiv.org/abs/2404.02543).
+
+## Test Results on Baidu-ULTR Expert Annotations
+
+| Model               | log-likelihood | DCG@1  | DCG@3  | DCG@5  | DCG@10 | nDCG@10 | MRR@10 |
+|---------------------|----------------|--------|--------|--------|--------|---------|--------|
+| Naive Pointwise     | 0.2272         | 1.6836 | 3.5616 | 4.8822 | 7.4244 | 0.3640  | 0.6096 |
+| **Naive Listwise**  | -              | 1.9738 | 4.1609 | 5.6861 | 8.5432 | 0.4091  | 0.6436 |
 
 ## Usage
+Here is an example with a mock input batch for how to download and call the model:
+
 ```Python
 import jax.numpy as jnp
 
@@ -58,9 +67,5 @@ outputs = model(batch)
 print(outputs)
 ```
 
-## Test Results on Baidu-ULTR Expert Annotations
+For more details on how to use the model with real data from Baidu-ULTR, take a look at the [evaluation script of our model repository](https://github.com/philipphager/baidu-bert-model/blob/main/eval.py).
 
-| Model               | log-likelihood | DCG@1  | DCG@3  | DCG@5  | DCG@10 | nDCG@10 | MRR@10 |
-|---------------------|----------------|--------|--------|--------|--------|---------|--------|
-| Naive Pointwise     | 0.2272         | 1.6836 | 3.5616 | 4.8822 | 7.4244 | 0.3640  | 0.6096 |
-| **Naive Listwise**  | -              | 1.9738 | 4.1609 | 5.6861 | 8.5432 | 0.4091  | 0.6436 |