Update README.md

README.md

@@ -9,6 +9,49 @@ This model was obtained by fine-tuning [google/pegasus-large](https://huggingfac
 Paper: [Understanding Iterative Revision from Human-Written Text](https://arxiv.org/abs/2203.03802) <br>
 Authors: Wanyu Du, Vipul Raheja, Dhruv Kumar, Zae Myung Kim, Melissa Lopez, Dongyeop Kang
 
+## Text Revision Task
+Given an edit intention for an original sentence, our model can generate a revised sentence.<br>
+The edit intentions are provided by [IteraTeR-full-sent](https://huggingface.co/datasets/wanyu/IteraTeR_full_sent) dataset, which are categorized as follows: 
+<table>
+  <tr>
+    <th>Edit Intention</th>
+    <th>Definition</th>
+    <th>Example</th>
+  </tr>
+  <tr>
+    <td>clarity</td>
+    <td>Make the text more formal, concise, readable and understandable.</td>
+    <td>
+    Original: The changes made the paper better than before. <br>
+    Revised: The changes improved the paper. 
+    </td>
+  </tr>
+  <tr>
+    <td>fluency</td>
+    <td>Fix grammatical errors in the text.</td>
+    <td>
+    Original: She went to the markt. <br>
+    Revised: She went to the market.
+    </td>
+  </tr>
+  <tr>
+    <td>coherence</td>
+    <td>Make the text more cohesive, logically linked and consistent as a whole.</td>
+    <td>
+    Original: She works hard. She is successful. <br>
+    Revised: She works hard; therefore, she is successful.
+    </td>
+  </tr>
+  <tr>
+    <td>style</td>
+    <td>Convey the writer’s writing preferences, including emotions, tone, voice, etc..</td>
+    <td>
+    Original: Everything was rotten. <br>
+    Revised: Everything was awfully rotten.
+    </td>
+  </tr>
+</table>
+
 ## Usage
 ```python
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM