Change text here and there

app.py

@@ -223,6 +223,24 @@ def highlight_entities():
     return HTML_WRAPPER.format(soup)
 
 
+def highlight_entities_new(summary_str: str):
+    st.session_state.summary_output = summary_str
+    summary_content = st.session_state.summary_output
+    markdown_start_red = "<mark class=\"entity\" style=\"background: rgb(238, 135, 135);\">"
+    markdown_start_green = "<mark class=\"entity\" style=\"background: rgb(121, 236, 121);\">"
+    markdown_end = "</mark>"
+
+    matched_entities, unmatched_entities = get_and_compare_entities(False)
+
+    for entity in matched_entities:
+        summary_content = summary_content.replace(entity, markdown_start_green + entity + markdown_end)
+
+    for entity in unmatched_entities:
+        summary_content = summary_content.replace(entity, markdown_start_red + entity + markdown_end)
+    soup = BeautifulSoup(summary_content, features="html.parser")
+    return HTML_WRAPPER.format(soup)
+
+
 def render_dependency_parsing(text: Dict):
     html = render_sentence_custom(text, nlp)
     html = html.replace("\n\n", "\n")
@@ -433,7 +451,7 @@ if summarize_button:
     # DEPENDENCY PARSING PART
     st.header("2️⃣ Dependency comparison")
     st.markdown(
-        "The second method we use for post-processing is called **Dependency parsing**: the process in which the "
+        "The second method we use for post-processing is called **Dependency Parsing**: the process in which the "
         "grammatical structure in a sentence is analysed, to find out related words as well as the type of the "
         "relationship between them. For the sentence “Jan’s wife is called Sarah” you would get the following "
         "dependency graph:")
@@ -455,7 +473,7 @@ if summarize_button:
                 "dependencies between article and summary (as we did with entity matching) would not be a robust method."
                 " More on the different sorts of dependencies and their description can be found [here](https://universaldependencies.org/docs/en/dep/).")
     st.markdown("However, we have found that **there are specific dependencies that are often an "
-                "indication of a wrongly constructed sentence** -when there is no article match. We (currently) use 2 "
+                "indication of a wrongly constructed sentence** when there is no article match. We (currently) use 2 "
                 "common dependencies which - when present in the summary but not in the article - are highly "
                 "indicative of factualness errors. "
                 "Furthermore, we only check dependencies between an existing **entity** and its direct connections. "
@@ -489,16 +507,18 @@ if summarize_button:
                 "empirically tested they are definitely not sufficiently robust for general use-cases.")
     st.markdown("####")
     st.markdown(
-        "Below we generate 3 different kind of summaries, and based on the two discussed methods, their errors are "
-        "detected to estimate a factualness score. Based on this basic approach, "
+        "*Below we generate 3 different kind of summaries, and based on the two discussed methods, their errors are "
+        "detected to estimate a summary score. Based on this basic approach, "
         "the best summary (read: the one that a human would prefer or indicate as the best one) "
-        "will hopefully be at the top. Summaries with the same scores will get the same rank displayed. We currently "
+        "will hopefully be at the top. We currently "
         "only do this for the example articles (for which the different summmaries are already generated). The reason "
-        "for this is that HuggingFace spaces are limited in their CPU memory.")
+        "for this is that HuggingFace spaces are limited in their CPU memory. We also highlight the entities as done "
+        "before, but note that the rankings are done on a combination of unmatched entities and "
+        "dependencies (with the latter not shown here).*")
     st.markdown("####")
 
     if selected_article != "Provide your own input" and article_text == fetch_article_contents(selected_article):
-        with st.spinner("Calculating more summaries and scoring them, this might take a minute or two..."):
+        with st.spinner("Fetching summaries, ranking them and highlighting entities, this might take a minute or two..."):
             summaries_list = []
             deduction_points = []
 
@@ -524,7 +544,8 @@ if summarize_button:
             cur_rank = 1
             rank_downgrade = 0
             for i in range(len(deduction_points)):
-                st.write(f'🏆 Rank {cur_rank} summary: 🏆', display_summary(summaries_list[i]), unsafe_allow_html=True)
+                #st.write(f'🏆 Rank {cur_rank} summary: 🏆', display_summary(summaries_list[i]), unsafe_allow_html=True)
+                st.write(f'🏆 Rank {cur_rank} summary: 🏆', highlight_entities_new(summaries_list[i]), unsafe_allow_html=True)
                 if i < len(deduction_points) - 1:
                     rank_downgrade += 1
                     if not deduction_points[i + 1] == deduction_points[i]: