Spaces:
Runtime error
Runtime error
Dmitry Kirsanov commited on
Commit ·
d66a76e
1
Parent(s): a9fdece
attr name fix
Browse files- understand.py +8 -6
understand.py
CHANGED
|
@@ -192,7 +192,9 @@ Output the line "ACTORS:" followed by your list of actors, one per line.
|
|
| 192 |
|
| 193 |
def annotate_actors(self):
|
| 194 |
sents = sent_tokenize(self.values.get("FAD"))
|
| 195 |
-
markup = "".join([f'<sentence
|
|
|
|
|
|
|
| 196 |
|
| 197 |
ret = self.query(
|
| 198 |
f"""Below is a document inside <document></document>. It is a {self.values.get("document type")}.
|
|
@@ -208,17 +210,17 @@ A reader of this document has compiled a list of actors (parties) mentioned or i
|
|
| 208 |
|
| 209 |
Your goal is to annotate each sentence of this document, inside a <sentence></sentence>, with its intended audience by picking one or more parties from this list. For each sentence, ask yourself: which of the parties from the list would want to know this sentence's information? Use only the parties from the list.
|
| 210 |
|
| 211 |
-
Add the relevant partes, separated by commas, inside the "
|
| 212 |
|
| 213 |
<example>
|
| 214 |
-
<sentence
|
| 215 |
</example>
|
| 216 |
|
| 217 |
-
Output just the document with the audience markup
|
| 218 |
|
| 219 |
<document>{markup}</document>""")
|
| 220 |
annotated = self.parse_document(ret)
|
| 221 |
-
self.values.put("FAD with
|
| 222 |
|
| 223 |
|
| 224 |
def ingest(self, filename):
|
|
@@ -244,7 +246,7 @@ Output just the document with the audience markup after each sentence, but other
|
|
| 244 |
"=== Concepts:\n"+newline.join(["- " + x for x in self.values.get("concepts")]),
|
| 245 |
"=== Actors:\n"+newline.join(["- " + x for x in self.values.get("actors")]),
|
| 246 |
"=== Actors, generalized:\n"+newline.join(["- " + x for x in self.values.get("actors, generalized")]),
|
| 247 |
-
"=== Document annotated:\n"+self.values.get("FAD with
|
| 248 |
)
|
| 249 |
|
| 250 |
|
|
|
|
| 192 |
|
| 193 |
def annotate_actors(self):
|
| 194 |
sents = sent_tokenize(self.values.get("FAD"))
|
| 195 |
+
markup = "".join([f'<sentence audience="">{x}</sentence>' for x in sents])
|
| 196 |
+
|
| 197 |
+
print(f"=== Sentence markup: {markup}")
|
| 198 |
|
| 199 |
ret = self.query(
|
| 200 |
f"""Below is a document inside <document></document>. It is a {self.values.get("document type")}.
|
|
|
|
| 210 |
|
| 211 |
Your goal is to annotate each sentence of this document, inside a <sentence></sentence>, with its intended audience by picking one or more parties from this list. For each sentence, ask yourself: which of the parties from the list would want to know this sentence's information? Use only the parties from the list.
|
| 212 |
|
| 213 |
+
Add the relevant partes, separated by commas, inside the "audience" attribute of each <sentence> tag. For example, suppose you have a document describing the game of Sudoku, and your parties are "Players" and "Creators". Here are example sentences with audience markup:
|
| 214 |
|
| 215 |
<example>
|
| 216 |
+
<sentence audience="Creators,Players">Sudoku is a popular logic puzzle with numbers with simple rules that even beginners can easily master.</sentence> <sentence audience="Creators">A presented puzzle with more than one possible solution would usually be considered defective.</sentence> <sentence audience="Players">If you have completed finding all positions for a number, draw an X over that number in the list outside.</sentence>
|
| 217 |
</example>
|
| 218 |
|
| 219 |
+
Output just the document with the audience markup sentence, but otherwise unchanged:
|
| 220 |
|
| 221 |
<document>{markup}</document>""")
|
| 222 |
annotated = self.parse_document(ret)
|
| 223 |
+
self.values.put("FAD with audience", annotated)
|
| 224 |
|
| 225 |
|
| 226 |
def ingest(self, filename):
|
|
|
|
| 246 |
"=== Concepts:\n"+newline.join(["- " + x for x in self.values.get("concepts")]),
|
| 247 |
"=== Actors:\n"+newline.join(["- " + x for x in self.values.get("actors")]),
|
| 248 |
"=== Actors, generalized:\n"+newline.join(["- " + x for x in self.values.get("actors, generalized")]),
|
| 249 |
+
"=== Document annotated:\n"+self.values.get("FAD with audience")
|
| 250 |
)
|
| 251 |
|
| 252 |
|