add babelscape reference

app.py

@@ -24,7 +24,7 @@ with st.sidebar:
     st.markdown("A [**Knowledge Base (KB)**](https://en.wikipedia.org/wiki/Knowledge_base) is information stored in structured data, ready to be used for analysis or inference. Usually a KB is stored as a graph (i.e. a [**Knowledge Graph**](https://www.ibm.com/cloud/learn/knowledge-graph)), where nodes are **entities** and edges are **relations** between entities.")
     st.markdown("_For example, from the text \"Fabio lives in Italy\" we can extract the relation triplet <Fabio, lives in, Italy>, where \"Fabio\" and \"Italy\" are entities._")
     st.header("How to build a Knowledge Graph")
-    st.markdown("To build a Knowledge Graph from text, we typically need to perform two steps:\n- Extract entities, a.k.a. **Named Entity Recognition (NER)**, i.e. the nodes.\n- Extract relations between the entities, a.k.a. **Relation Classification (RC)**, i.e. the edges.\nRecently, end-to-end approaches have been proposed to tackle both tasks simultaneously. This task is usually referred to as **Relation Extraction (RE)**. In this demo, an end-to-end model called [**REBEL**](https://github.com/Babelscape/rebel/blob/main/docs/EMNLP_2021_REBEL__Camera_Ready_.pdf) is used.")
+    st.markdown("To build a Knowledge Graph from text, we typically need to perform two steps:\n- Extract entities, a.k.a. **Named Entity Recognition (NER)**, i.e. the nodes.\n- Extract relations between the entities, a.k.a. **Relation Classification (RC)**, i.e. the edges.\nRecently, end-to-end approaches have been proposed to tackle both tasks simultaneously. This task is usually referred to as **Relation Extraction (RE)**. In this demo, an end-to-end model called [**REBEL**](https://github.com/Babelscape/rebel/blob/main/docs/EMNLP_2021_REBEL__Camera_Ready_.pdf) is used, trained by [Babelscape](https://babelscape.com/).")
     st.header("How REBEL works")
     st.markdown("REBEL is a **text2text** model obtained by fine-tuning [**BART**](https://huggingface.co/docs/transformers/model_doc/bart) for translating a raw input sentence containing entities and implicit relations into a set of triplets that explicitly refer to those relations. You can find [REBEL in the Hugging Face Hub](https://huggingface.co/Babelscape/rebel-large).")
     st.header("Further steps")