Update README.md

README.md

@@ -13,8 +13,12 @@ model-index:
 
 # scientific-challenges-and-directions
 
-We present a novel resource to help scientists and medical professionals discover challenges and potential directions across scientific literature, focusing on a broad corpus pertaining to the COVID-19 pandemic and related historical research.   
+We present a novel resource to help scientists and medical professionals discover challenges and potential directions across scientific literature, focusing on a broad corpus pertaining to the COVID-19 pandemic and related historical research. At a high level, the _challenges_ and _directions_ are defined as follows:
 
+* **Challenge**: A sentence mentioning a problem, difficulty, flaw, limitation, failure, lack of clarity, or knowledge gap.
+* **Research direction**: A sentence mentioning suggestions or needs for further research, hypotheses, speculations, indications or hints that an issue is worthy of exploration.  
+
+* This model here is described in our paper: [A Search Engine for Discovery of Scientific Challenges and Directions](https://arxiv.org/abs/2108.13751) (though we've upgraded the infrastructure since the paper release so there are slight differences in the resulrs).
 * Please cite our paper if you use our datasets or models in your project. See the [BibTeX](#citation). 
 * Feel free to [email us](#contact-us). 
 * Also, check out [our search engine](https://challenges.apps.allenai.org/), as an example application.
@@ -22,9 +26,9 @@ We present a novel resource to help scientists and medical professionals discove
 ## Model description
 This model is a fine-tuned version of [PubMedBERT](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on the X dataset, designed for multi-label text classification.
 
-## Training and evaluation data
 
-More information needed
+## Training and evaluation data
+The scientific-challenges-and-directions model is trained based on a dataset that is a collection of 2894 sentences and their surrounding contexts, from 1786 full-text papers in the CORD-19 corpus, labeled for classification of challenges and directions by expert annotators with biomedical and bioNLP backgrounds. For full details on the train/test/split of the data see section 3.1 in our [paper](https://arxiv.org/abs/2108.13751)
 
 ## Training procedure
 
@@ -58,3 +62,24 @@ The achieves the following results on the test set:
 - Pytorch 1.10.0+cu111
 - Datasets 1.17.0
 - Tokenizers 0.10.3
+
+## Citation
+
+If using our dataset and models, please cite:
+
+```
+@misc{lahav2021search,
+      title={A Search Engine for Discovery of Scientific Challenges and Directions}, 
+      author={Dan Lahav and Jon Saad Falcon and Bailey Kuehl and Sophie Johnson and Sravanthi Parasa and Noam Shomron and Duen Horng Chau and Diyi Yang and Eric Horvitz and Daniel S. Weld and Tom Hope},
+      year={2021},
+      eprint={2108.13751},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```
+
+## Contact us
+
+Please don't hesitate to reach out.
+
+**Email:** `[email protected]`,`[email protected]`.