Update app.py

app.py

@@ -20,34 +20,37 @@ def check_lang(lang_acronym):
     else: 
         return "False"
     
-title = "DReAM: version I"
+title = "DReAM"
 
 description_main = """
-A set of pre-trained LLMs tuned to perform different tasks over a "very specific" set of textual reports. 
-Available tasks include: 
+This space allows access to a set of LLMs tuned to perform different tasks over dream reports. 
+Two main tasks are available: 
 
-- Sentiment Analysis (SA) (available both Englis-only or multilingual)
+- Sentiment Analysis (SA), with two English-only models (one for classification, one for generation) and a large multilingual model for classification.
 
-- Name Entity Recognition (NER)
+- Name Entity Recognition (NER), with an English-only model that generates the identified characters. 
 
-Use the current interface to check if a language is included in the multilingual SA model, using language acronyms (e.g. it for Italian).
-Use the tabs above the title to directly query and test the different models.
+All models have been tuned on the Hall and Vand de Castle framework. More details are on the page for each model. For more on the training framework, see the [Bertolini et al., 2023](https://arxiv.org/pdf/2302.14828.pdf) preprint.
+
+Use the current interface to check if a language is included in the multilingual SA model, using language acronyms (e.g. it for Italian). the tabs above will direct you to each model to query.
+
+If you want to use the models outside the space, you can easily do so via [DReAMy](https://github.com/lorenzoscottb/DReAMy)
 """
 
 description_L = """
-XLM-R tuned model, EN-tuned, pre-trained with 94 languages available (see original model [card](https://huggingface.co/xlm-roberta-large) to see which are available)
+This model is an XLM-R tuned model, pre-trained with 94 languages available, and tuned on emotion-annotated DreamBank English data. (see original model [card](https://huggingface.co/xlm-roberta-large) to see which are available)
 """
 
 description_S = """
-A BERT-base-cased model pre-trained and tuned on English data.
+A BERT-base-cased model pre-trained on Eglish-only text and tuned on annotated DreamBank English data..
 """
 
 description_G = """
-A t5 model tuned to performer text-generation, and predict emotion as well as the character experiencing those emotions.
+A T5 model tuned to performer text generation, and predict emotion as well as the character experiencing those emotions.
 """
 
 description_GNER = """
-A t5 model tuned to performer text-generation, and predict which characters are present in the report.
+A T5 model tuned to performer text generation, and predict which characters are present in the report. Note that, in the Hall and Van de Castle, the character lists never includes the dreamer. Hence, if you (willingly or not) enter a report that does not contain another character reference, the model will/should (correctly) produce an empty string. Moreover, it is likely that the produced list of CHAR could be longer than the one produced by the SA model, as not all CHAR might be associated with emotions. 
 """
 
 example_main = ["en", "it", "pl"]