Spaces:
Runtime error
Runtime error
Dmitry Kirsanov commited on
Commit ·
93bd36d
1
Parent(s): 7f13e9d
more hand-holding
Browse files- understand.py +19 -7
understand.py
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
import re
|
|
|
|
| 2 |
from nltk.tokenize import sent_tokenize
|
| 3 |
import nltk
|
| 4 |
nltk.download('punkt')
|
|
@@ -144,7 +145,7 @@ Here's the document:
|
|
| 144 |
set2 = set(two_attempts[1][what['plural']])
|
| 145 |
jackard[what['plural']] = len(set1.intersection(set2)) / len(set1.union(set2))
|
| 146 |
if set1 != set2:
|
| 147 |
-
print(f"===Two attempts of {what['plural']} are different,
|
| 148 |
ret = self.query(
|
| 149 |
f"""Below is a document inside <document></document>. It is a {self.values.get("document type")}.
|
| 150 |
|
|
@@ -240,22 +241,33 @@ Output just the document with the audience markup sentence, but otherwise unchan
|
|
| 240 |
self.values.put("FAD with audience, diff", diff)
|
| 241 |
|
| 242 |
def split_document(self):
|
|
|
|
|
|
|
|
|
|
| 243 |
ret = self.query(
|
| 244 |
-
f"""Below is a document inside <document></document>. It is a {self.values.get("document type")}.
|
| 245 |
|
| 246 |
Summary of the document:
|
| 247 |
{self.values.get("summary")}
|
| 248 |
|
| 249 |
Read the entire document carefully. Remember everything you know about the concepts it touches.
|
| 250 |
|
| 251 |
-
|
| 252 |
|
| 253 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 254 |
|
| 255 |
-
|
| 256 |
|
| 257 |
-
|
| 258 |
-
self.values.put(f"""FAD for {self.values.get("actors, generalized")[0]}""", ret)
|
| 259 |
|
| 260 |
|
| 261 |
def ingest(self, filename):
|
|
|
|
| 1 |
import re
|
| 2 |
+
import xml.etree.ElementTree as ET
|
| 3 |
from nltk.tokenize import sent_tokenize
|
| 4 |
import nltk
|
| 5 |
nltk.download('punkt')
|
|
|
|
| 145 |
set2 = set(two_attempts[1][what['plural']])
|
| 146 |
jackard[what['plural']] = len(set1.intersection(set2)) / len(set1.union(set2))
|
| 147 |
if set1 != set2:
|
| 148 |
+
print(f"===Two attempts of {what['plural']} are different, jaccard similarity: {jackard[what['plural']]}")
|
| 149 |
ret = self.query(
|
| 150 |
f"""Below is a document inside <document></document>. It is a {self.values.get("document type")}.
|
| 151 |
|
|
|
|
| 241 |
self.values.put("FAD with audience, diff", diff)
|
| 242 |
|
| 243 |
def split_document(self):
|
| 244 |
+
audience = self.values.get("actors, generalized")[0]
|
| 245 |
+
derivative_string = f"<document>{self.values.get("FAD with audience")}</document>"
|
| 246 |
+
derivative = newline.join(ET.fromstring(derivative_string).fiindall(f"//sentence[contains(@audience,'{audience}')]/text()"))
|
| 247 |
ret = self.query(
|
| 248 |
+
f"""Below is a document inside <document>...</document>. It is a {self.values.get("document type")}.
|
| 249 |
|
| 250 |
Summary of the document:
|
| 251 |
{self.values.get("summary")}
|
| 252 |
|
| 253 |
Read the entire document carefully. Remember everything you know about the concepts it touches.
|
| 254 |
|
| 255 |
+
An editor was tasked with creative a derivative document that is addressed to {audience}. The editor compiled all sentences from the document that have information relevant for {audience}. These sentences are dumped below the main document inside <derivative-document for="{audience}">...</derivative-document>.
|
| 256 |
|
| 257 |
+
Your goal is to edit the derivative document for consistency. Rearrange its sentences in a way that makes sense for a reader. If necessary, write, or adapt from the original <document>, connecting sentences.
|
| 258 |
+
|
| 259 |
+
Here's the otiginal document:
|
| 260 |
+
|
| 261 |
+
<document>{self.values.get("FAD")}</document>
|
| 262 |
+
|
| 263 |
+
Here's the derivative document that you need to edit:
|
| 264 |
+
|
| 265 |
+
<derivative-document for="{audience}">{derivative}</derivative-document>
|
| 266 |
|
| 267 |
+
Output just your revision inside <derivative-document>...</derivative-document>.
|
| 268 |
|
| 269 |
+
""")
|
| 270 |
+
self.values.put(f"""FAD for {self.values.get("actors, generalized")[0]}""", self.parse_document(ret))
|
| 271 |
|
| 272 |
|
| 273 |
def ingest(self, filename):
|