Dmitry Kirsanov commited on
Commit
199ce86
·
1 Parent(s): 2faa652

better explaining

Browse files
Files changed (1) hide show
  1. understand.py +4 -6
understand.py CHANGED
@@ -180,7 +180,7 @@ A reader of this document has compiled a list of actors mentioned or implied in
180
 
181
  {newline.join(["- " + x for x in self.values.get("actors")])}
182
 
183
- Your goal is to generalize this list, replacing groups of actors playing the same or similar roles with their generic term. If an actor is not very relevant to the document (that is, you cannot see this document as written by, for, or about this actor), then drop it altogether. Try to pare this list down as much as possible, leaving only the most important categories of actors.
184
 
185
  Output the line "ACTORS:" followed by your list of actors, one per line.
186
 
@@ -202,13 +202,11 @@ A reader of this document has compiled a list of actors (parties) mentioned or i
202
 
203
  {newline.join(["- " + x for x in self.values.get("actors")])}
204
 
205
- Your goal is to annotate each sentence of this document with its intended audience, by picking parties from this list. For each sentence, ask yourself: which of the parties from the list would benefit from this sentence's information? Add the relevant partes, separated by commas, after the end of the sentence in [[double brackets]].
206
 
207
- For example, imagine you have a document describing the process of submitting a scientific paper for publication, and your parties are "Authors" and "Publishers". Here are example sentences with audience markup:
208
 
209
- Format the references in your paper according to journal guidelines..[[Authors]]
210
- Ensure the papers submitted through the online platform are indexed in relevant databases and repositories.[[Publishers]]
211
- The journey of the manuscript begins with an initial editorial review conducted by journal editors.[[Authors,Publishers]]
212
 
213
  Output just the document with the audience markup after each sentence, but otherwise unchanged.
214
 
 
180
 
181
  {newline.join(["- " + x for x in self.values.get("actors")])}
182
 
183
+ Your goal is to generalize this list, replacing groups of actors playing the same or similar roles with their generic term. If an actor is not very relevant to the document (that is, you cannot see this document as written by, for, or about this actor), then drop it altogether. Also, drop any inanimate actors, leaving only categories of persons. Overall, pare this list down as much as possible, leaving only the most important categories of actors.
184
 
185
  Output the line "ACTORS:" followed by your list of actors, one per line.
186
 
 
202
 
203
  {newline.join(["- " + x for x in self.values.get("actors")])}
204
 
205
+ Your goal is to annotate each sentence of this document with its intended audience, by picking parties from this list. For each sentence, ask yourself: which of the parties from the list would benefit from this sentence's information? Use only the parties from the list; add the relevant partes, separated by commas, after the end of each sentence in [[double brackets]]. If several sentences in a row have the same audience, you can only mark the last one.
206
 
207
+ For example, suppose you have a document describing the process of submitting a scientific paper for publication, and your parties are "Authors" and "Publishers". Here are example sentences with audience markup:
208
 
209
+ The journey of the manuscript begins with an initial editorial review conducted by journal editors.[[Authors,Publishers]] Format the references in your paper according to journal guidelines.[[Authors]] Ensure the papers submitted through the online platform are indexed in relevant databases and repositories.[[Publishers]]
 
 
210
 
211
  Output just the document with the audience markup after each sentence, but otherwise unchanged.
212