Create README.md

README.md

@@ -0,0 +1,10 @@
+# Culinary Roberta
+
+I call this `roberta` as I only did language adaptation using MLM.
+
+This model starts from BERT-BASE. I ran a MLM language adaptation stage based on:
+* The steps and ingredients of the `recipe_nlg` dataset.
+* Food-related books found on project gutenberg.
+* Food blogs scraped from the internet.
+
+After this, I fine-tune it as a sentence-pair classification, based on ingredient synonyms using WordNet.