reformat

app.py

@@ -9,6 +9,28 @@ model = AutoModelForSeq2SeqLM.from_pretrained("fangyuan/lfqa_role_classification
 tokenizer = AutoTokenizer.from_pretrained("fangyuan/lfqa_role_classification")
 en_nlp = stanza.Pipeline('en', processors='tokenize')
 
+
+article='''
+# Discourse Structure of Long-form Answers.
+## About 
+This is a demo for our paper: [How Do We Answer Complex Questions: Discourse Structure of Long-form Answers](https://aclanthology.org/2022.acl-long.249/).
+Fangyuan Xu, Junyi Jessy Li, Eunsol Choi. 2022.
+Contact: [Fangyuan Xu](https://www.cs.utexas.edu/~fxu/) via firstname@utexas.edu
+## Model
+The model served here is a T5(large)-based role classification model trained on functional roles of ELI5 answers.
+## Resources 
+Please see more information (paper/code/data/datasheet) at our [website](https://www.cs.utexas.edu/~fxu/lfqa_discourse/index.html)!
+'''
+
+role_mappings = {
+    'Answer': 'Answer',
+    'Answer (Summary)': 'Summary',
+    'Auxiliary Information': 'Auxiliary Information',
+    'Answer - Example': 'Example',
+    'Miscellaneous': 'Miscellaneous',
+    'Answer - Organizational sentence': 'Organizational sentence',
+}
+
 def get_ans_sentence_with_stanza(answer_paragraph, pipeline,
                                  is_offset=False):
     '''sentence segmentation with stanza'''
@@ -35,7 +57,6 @@ def create_input_to_t5(question, answer):
 def process_t5_output(input_txt, output_txt):
     pred_roles = []
     answer_sentence = re.split('\[\d+\] ', input_txt)
-    question = answer_sentence[0].strip()
     answer_sentence = answer_sentence[1:]
     sentence_idx = re.findall('\[\d+\]', input_txt)
     idx_to_sentence = zip(sentence_idx, answer_sentence)
@@ -45,7 +66,10 @@ def process_t5_output(input_txt, output_txt):
         idx: role.strip() for (idx, role) in zip(pred_idx, pred_role)
     }
     for _, (idx, sentence) in enumerate(idx_to_sentence):
-        pred_roles.append(' ' if idx not in idx_to_role else idx_to_role[idx])
+        pred_role = ' ' if idx not in idx_to_role else idx_to_role[idx]
+        mapped_pred_role = role_mappings[pred_role]
+        pred_roles.append('{}: {}'.format(sentence, mapped_pred_role))
+    pred_roles.append(output_txt)
     return '\n'.join(pred_roles)
 
 
@@ -71,7 +95,9 @@ gr.Interface(
     theme="peach",
     title="Discourse structure of long-form answer",
     description="Input a question with its long-form answer to see the predicted discourse structure by our role classifier.",
+    article=article,
     examples=[
+        #['', '']
     ]
 ).launch(enable_queue=True)