Spaces:
Sleeping
Sleeping
mohdelgaar
commited on
Commit
β’
fbe88e2
1
Parent(s):
54ba470
Style
Browse files
app.py
CHANGED
@@ -228,7 +228,7 @@ title = """
|
|
228 |
The model can generate diverse paraphrases of a given sentence, each adjusted to maintain consistent meaning while varying
|
229 |
in linguistic complexity according to the desired level.</p>
|
230 |
<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").
|
231 |
-
To ensure high-quality outputs, our approach
|
232 |
achievable set of indices for the given target.</p>
|
233 |
"""
|
234 |
|
@@ -247,19 +247,18 @@ paraphrase generation). Then, click "Generate."
|
|
247 |
**Manual Linguistic Control**: Select this option to manually control the linguistic complexity of the
|
248 |
generated text. We provided a set of tools for manual adjustments of the desired linguistic complexity of
|
249 |
the target sentence. These tools enable the user to extract linguistic indices from a given sentence,
|
250 |
-
generate a random (yet coherent) set of linguistic indices, and add or
|
251 |
These tools are designed for experimental use and require the user to possess linguistic expertise for
|
252 |
effective input of linguistic indices. To use these tools, select "Tools to assist in setting linguistic
|
253 |
indices." Once indices are entered, click "Generate."
|
254 |
|
255 |
|
256 |
-
Second, you may select to use exact or approximate computation of linguistic indices
|
257 |
-
in quality control of the genration). Approximate computation is significantly faster.
|
258 |
|
259 |
-
Third, you may view the intermediate sentences of the quality control process by selecting the checkbox.
|
260 |
|
261 |
-
Fourth, you may try out some examples by clicking on "Examples...". Examples consist of a source sentences
|
262 |
-
|
263 |
|
264 |
Please make your choice below.
|
265 |
|
@@ -291,13 +290,13 @@ body {
|
|
291 |
|
292 |
.top-separator {
|
293 |
width: 100%;
|
294 |
-
height:
|
295 |
background-color: #000; /* Adjust the color as needed */
|
296 |
margin-top: 20px; /* Adjust the margin as needed */
|
297 |
}
|
298 |
.bottom-separator {
|
299 |
width: 100%;
|
300 |
-
height:
|
301 |
background-color: #000; /* Adjust the color as needed */
|
302 |
margin-bottom: 20px; /* Adjust the margin as needed */
|
303 |
}
|
@@ -319,7 +318,7 @@ with gr.Blocks(
|
|
319 |
with gr.Group(elem_id='mode'):
|
320 |
mode = gr.Radio(
|
321 |
value='Randomized Paraphrase Generation',
|
322 |
-
label='
|
323 |
type="index",
|
324 |
choices=['π Randomized Paraphrase Generation',
|
325 |
'βοΈ Complexity-Matched Paraphrasing',
|
|
|
228 |
The model can generate diverse paraphrases of a given sentence, each adjusted to maintain consistent meaning while varying
|
229 |
in linguistic complexity according to the desired level.</p>
|
230 |
<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").
|
231 |
+
To ensure high-quality outputs, our approach iteratively adjusts the generated text to match the closest, yet coherent
|
232 |
achievable set of indices for the given target.</p>
|
233 |
"""
|
234 |
|
|
|
247 |
**Manual Linguistic Control**: Select this option to manually control the linguistic complexity of the
|
248 |
generated text. We provided a set of tools for manual adjustments of the desired linguistic complexity of
|
249 |
the target sentence. These tools enable the user to extract linguistic indices from a given sentence,
|
250 |
+
generate a random (yet coherent) set of linguistic indices, and add or subtract to them.
|
251 |
These tools are designed for experimental use and require the user to possess linguistic expertise for
|
252 |
effective input of linguistic indices. To use these tools, select "Tools to assist in setting linguistic
|
253 |
indices." Once indices are entered, click "Generate."
|
254 |
|
255 |
|
256 |
+
Second, you may select to use exact or approximate computation of linguistic indices. Approximate computation is significantly faster.
|
|
|
257 |
|
258 |
+
Third, you may view the intermediate sentences of the quality control process by selecting the checkbox under "Advanced Options".
|
259 |
|
260 |
+
Fourth, you may try out some examples by clicking on "Examples...". Examples consist of a source sentences
|
261 |
+
and a sample set of target linguistic indices.
|
262 |
|
263 |
Please make your choice below.
|
264 |
|
|
|
290 |
|
291 |
.top-separator {
|
292 |
width: 100%;
|
293 |
+
height: 4px; /* Adjust the height for boldness */
|
294 |
background-color: #000; /* Adjust the color as needed */
|
295 |
margin-top: 20px; /* Adjust the margin as needed */
|
296 |
}
|
297 |
.bottom-separator {
|
298 |
width: 100%;
|
299 |
+
height: 4px; /* Adjust the height for boldness */
|
300 |
background-color: #000; /* Adjust the color as needed */
|
301 |
margin-bottom: 20px; /* Adjust the margin as needed */
|
302 |
}
|
|
|
318 |
with gr.Group(elem_id='mode'):
|
319 |
mode = gr.Radio(
|
320 |
value='Randomized Paraphrase Generation',
|
321 |
+
label='Operation Modes',
|
322 |
type="index",
|
323 |
choices=['π Randomized Paraphrase Generation',
|
324 |
'βοΈ Complexity-Matched Paraphrasing',
|