Update README.md

README.md

@@ -14,7 +14,13 @@ license: apache-2.0
 
 ## Model description
 
-[More Information Needed]
+This model was trained to predict the presence of causal relations between two headlines. This model is for the Simple task with 3 possible labels: A causes B, B causes A, no causal relation. English and Russian languages are supported.
+
+You can use hosted inference API to infer a label for a headline pair. To do this, you shoud seperate headlines with </s> token.
+For example:
+```
+Песков опроверг свой перевод на удаленку</s>Дмитрий Песков перешел на удаленку
+```
 
 ## Intended uses & limitations
 
@@ -63,19 +69,21 @@ pipe_predict(texts, pipe)
 
 #### Limitations and bias
 
-[More Information Needed]
+The models are intended to be used on news headlines. No other limitations are known.
 
 ## Training data
 
-[More Information Needed]
+* HuggingFace dataset: [IlyaGusev/headline_cause](https://huggingface.co/datasets/IlyaGusev/headline_cause)
+* GitHub: [IlyaGusev/HeadlineCause](https://github.com/IlyaGusev/HeadlineCause)
 
 ## Training procedure
 
-[More Information Needed]
+* Notebook: [HeadlineCause](https://colab.research.google.com/drive/1NAnD0OJ0TnYCJRsHpYUyYkjr_yi8ObcA)
+* Stand-alone script: [train.py](https://github.com/IlyaGusev/HeadlineCause/blob/main/headline_cause/train.py)
 
 ## Eval results
 
-[More Information Needed]
+Evaluation results can be found in the [arxiv paper](https://arxiv.org/pdf/2108.12626.pdf).
 
 ### BibTeX entry and citation info
 
@@ -88,4 +96,4 @@ pipe_predict(texts, pipe)
       archivePrefix={arXiv},
       primaryClass={cs.CL}
 }
-```
+```