Update app.py

app.py

@@ -33,14 +33,29 @@ def test_input(words):
 # )
 
     
-title = "BERT on a PLANE"
+title = "**BERT on a PLANE**"
 
 description = """
 Did you know that, logically speaking, a small cat is not a small animal, and that a fake smile is not a smile?
 
 
-Learn more testing our BERT model is tuned to perform phrase-level adjective-noun entailment, via the [PLANE](https://aclanthology.org/2022.coling-1.359/) dataset.
+Learn more by testing our BERT model tuned to perform phrase-level adjective-noun entailment, via the [PLANE](https://aclanthology.org/2022.coling-1.359/) dataset.
 
+**Intended uses & limitations**:
+
+The scope of the model is not to run lexical entailment or hypernym detection (e.g., *"A dog is an animal*"), but to perform a very specific subset of phrase-level entailment, based on adjective-nouns phrases. The type of question you can ask the model are limited, and should have one of three forms:
+
+- An adjective+Noun is a Noun (e.g. A red car is a car)
+
+- An adjective+Noun is a noun-hypernym (e.g. A red car is a vehicle)
+
+- An adjective+Noun is a adjective+noun-hypernym (e.g. A red car is a red vehicle)
+
+Linguistically speaking, adjectives belong to three macro classes (intersective, subsective, and intensional). From a linguistic and logical stand, these class shape the truth value of the three forms above. For instance, since red is an intersective adjective, the three from are all true. A subjective adjective like small allows just the first two, but not the last – that is, logically speaking, a small car is not a small vehicle.
+
+In other words, the model was built to study out-of-distribution compositional generalisation with respect to a very specific set of compositional phenomena.
+
+This poses clear limitations to the question you can ask the model. For instance, if you had to query the model with a basic (false) hypernym detection task (e.g., *A dog is a cat*), the model will consider it as true.
 
 The current model achieves an accuracy of 90% on out-of-distribution evaluation
 Coming soon: check if words were in training data!"""