Targeted rewrites
A method for providing targeted rewrites can include receiving a selection of text in a file; generating a set of target rewrites of the selection of text, the set of target rewrites comprising: at least one phrase or sentence having semantic similarity to a phrase or sentence of the selection of text; and a style that corresponds to a particular target style, wherein a target style is a representative style for a genre, profession, or environment; and providing for selection one or more of the target rewrites of the set of target rewrites.
1. A method for providing targeted rewrites, comprising:
receiving a selection of text in a file of a first application file format and target information comprising a second application file format, wherein the selection of text in the file of the first application file format has a first style of an informal style for a profession and a particular target style is of a formal style for a profession;
identifying one or more target styles for the second application file format;
converting the selection of text from the first application file, format to a set of target rewrites suitable for the second application file format by generating the set of target rewrites of the selection of text, the set of target rewrites comprising:
at least one phrase or sentence having semantic similarity to a phrase or sentence of the selection of text; and
a style that corresponds to the particular target style of the one or more target styles for the second application file format, wherein a target style is a representative style for a genre, profession, or environment;
providing one or more of the target rewrites of the set of target rewrites suitable for the second application file format; and
replacing the selection of text in the file with a target rewrite of the one or more of the target rewrites suitable for the second application file format,
wherein generating the set of target rewrites comprises analyzing the text using a targeted rewrite engine.
2. The method of claim 1 , wherein the target information comprises an explicit indicator of the second application file format.
3. The method of claim 1 , wherein the target information comprises a natural language statement from a user indicative of the second application file format.
4. The method of claim 1 , wherein the target information further comprises context information, wherein the context information comprises an application name of an application for which the text is being created or consumed, a user name associated with the selection of text, a file name of the file, other content in the file, or a combination thereof.
5. The method of claim 1 , wherein the targeted rewrite engine comprises a neural network.
6. The method of claim 1 , wherein the selection of text comprises a number of characters before text expressly selected by a user, a number of characters after text expressly selected by the user, a number of characters both before and after text expressly selected by the user, an entire text of the file, or a portion of text expressly selected by the user.
7. The method of claim 1 , wherein the file is a document, a message item, or a chat channel item.
8. A system for providing targeted rewrites, comprising:
a processing system;
a storage system; and
instructions stored on the storage system that direct the system for providing targeted rewrites to at least:
receive, from a source a selection of text in a file of a first application file format;
receive target information comprising a second application file format;
determine a target from the target information comprising the second application file format;
identify one or more target styles for the determined target associated with the second application file format, wherein a target style is a representative style for a genre, profession, or environment;
convert the selection of text from the first application file format to a set of target rewrites suitable for the second application file format by generating the set of target rewrites of the selection of text, the set of target rewrites comprising:
at least one phrase or sentence having semantic similarity to a phrase or sentence of the selection of text; and
a style that corresponds to a particular target style of the one or more target styles for the second application file format; and
communicate, to the source, one or more of the target rewrites of the set of target rewrites suitable for the second application file format,
wherein the instructions to generate the set of target rewrites direct the system to at least analyze the text using a targeted rewrite engine.
9. The system of claim 8 , wherein the targeted rewrite engine comprises a neural network.
10. The system of claim 8 , wherein the target indicates which model is used by the targeted rewrite engine.
11. One or more computer readable storage media having instructions stored thereon that when executed by a computing system, direct the computing system to:
receive a selection of text in a file of a first application file format and target information comprising a second application file format;
identify one or more target styles for the second application file format;
convert the selection of text from the first application file format to a set of target rewrites suitable for the second application file format by generating the set of target rewrites of the selection of text, the set of target rewrites comprising:
at least one phrase or sentence having semantic similarity to a phrase or, sentence of the selection of text; and
a style that corresponds to a particular target style of the one or more target styles for the second application file format, wherein a target style is a representative style for a genre, profession, or environment;
provide one or more of the target rewrites of the set of target rewrites suitable for the second application file format; and
replace the selection of text in the file with a target rewrite of the one or more of the target rewrite suitable for the second application file format,
wherein the instructions to generate the set of target rewrites direct the computing system to at least analyze, the text using a targeted rewrite engine.
12. The one or more media of claim 11 , wherein the target information comprises an explicit indicator of the second application file format.
13. The one or more media of claim 11 , wherein the target information comprises a natural language statement from a user indicative of the second application file format.
14. The one or more media of claim 11 , wherein the target information further comprises context information, wherein the context information comprises an application name of an application for which the text is being created or consumed, a user name associated with the selection of text, a file name of the file, other content in the file, or a combination thereof.
15. The one or more media of claim 11 , wherein the file is a document, a message item, or a chat channel item.
16. The one or more media of claim 11 , wherein the selection of text in the file of the first application file format has a first style of an informal style for a profession and the particular target style is of a formal style for a profession.