Update README.md

README.md

@@ -20,13 +20,12 @@ widget:
 A fine-tuned [`distilbert-base-cased`](https://huggingface.co/distilbert-base-cased) model trained on historical newspapers from the [Heritage Made Digital collection](https://huggingface.co/datasets/davanstrien/hmd-erwt-training) with temporal metadata. 
 
 
-**Note**: This model was trained for experimental purposes, please use it with care. 
+**Warning**: This model was trained for **experimental purposes**, please use it with care. 
 
 
+You find more detailed information below and in our working paper ["Metadata Might Make Language Models Better"](https://drive.google.com/file/d/1Xp21KENzIeEqFpKvO85FkHynC0PNwBn7/view?usp=sharing).
 
-You find more detailled information below and in our working paper ["Metadata Might Make Language Models Better"](https://drive.google.com/file/d/1Xp21KENzIeEqFpKvO85FkHynC0PNwBn7/view?usp=sharing).
-
-## Background
+## Background and Data
 
 ERWT was created using a MetaData Masking Approach (or MDMA 💊), in which we train a Masked Language Model simultaneously on text and metadata. Our intuition was that incorporating information that is not explicitly present in the text—such as the time of publication or the political leaning of the author—may make language models "better" in the sense of being more sensitive to historical and political aspects of language use.
 
@@ -37,7 +36,9 @@ For example, we would format a snippet of text taken from the [Londonderry Senti
 "1870 [DATE] Every scrap of intelligence relative to the war between France and Prussia is now read with interest."
 ```
 
-... and then provide this sentence with prepended temporal metadata to MLM. This effectively
-
+... and then provide this sentence with prepended temporal metadata to MLM. 
 
 ## Intended uses & limitations
+
+Exposing the model to extra-textual information allows us to use **language change** and **date prediction**
+