Style

app.py

@@ -228,7 +228,7 @@ title = """
 The model can generate diverse paraphrases of a given sentence, each adjusted to maintain consistent meaning while varying
 in linguistic complexity according to the desired level.</p>
 <p style="font-size:1.2em;">It is important to note that not all index combinations are feasible (e.g., a sentence of "length" 5 with 10 "unique words").
-To ensure high-quality outputs, our approach interpolates the embeddings of linguistic indices to identify the closest,
+To ensure high-quality outputs, our approach iteratively adjusts the generated text to match the closest, yet coherent
 achievable set of indices for the given target.</p>
 """
 
@@ -247,19 +247,18 @@ paraphrase generation). Then, click "Generate."
 **Manual Linguistic Control**: Select this option to manually control the linguistic complexity of the
 generated text. We provided a set of tools for manual adjustments of the desired linguistic complexity of
 the target sentence. These tools enable the user to extract linguistic indices from a given sentence,
-generate a random (yet coherent) set of linguistic indices, and add or remove noise from the indices.
+generate a random (yet coherent) set of linguistic indices, and add or subtract to them.
 These tools are designed for experimental use and require the user to possess linguistic expertise for
 effective input of linguistic indices. To use these tools, select "Tools to assist in setting linguistic
 indices." Once indices are entered, click "Generate."
 
 
-Second, you may select to use exact or approximate computation of linguistic indices (used in mode (2) and
-in quality control of the genration). Approximate computation is significantly faster.
+Second, you may select to use exact or approximate computation of linguistic indices. Approximate computation is significantly faster.
 
-Third, you may view the intermediate sentences of the quality control process by selecting the checkbox.
+Third, you may view the intermediate sentences of the quality control process by selecting the checkbox under "Advanced Options".
 
-Fourth, you may try out some examples by clicking on "Examples...". Examples consist of a source sentences,
-the indices of the source sentences, and a sample set of target linguistic indices.
+Fourth, you may try out some examples by clicking on "Examples...". Examples consist of a source sentences
+and a sample set of target linguistic indices.
 
 Please make your choice below.
 
@@ -291,13 +290,13 @@ body {
 
 .top-separator {
   width: 100%;
-  height: 3px; /* Adjust the height for boldness */
+  height: 4px; /* Adjust the height for boldness */
   background-color: #000; /* Adjust the color as needed */
   margin-top: 20px; /* Adjust the margin as needed */
 }
 .bottom-separator {
   width: 100%;
-  height: 3px; /* Adjust the height for boldness */
+  height: 4px; /* Adjust the height for boldness */
   background-color: #000; /* Adjust the color as needed */
   margin-bottom: 20px; /* Adjust the margin as needed */
 }
@@ -319,7 +318,7 @@ with gr.Blocks(
     with gr.Group(elem_id='mode'):
         mode = gr.Radio(
                 value='Randomized Paraphrase Generation',
-                label='How would you like to use this system?',
+                label='Operation Modes',
                 type="index",
                 choices=['🔄 Randomized Paraphrase Generation',
                          '⚖️ Complexity-Matched Paraphrasing',