Transformation
  • PDF

Transformation

  • PDF

Available in Classic and VPC

Transformation introduces referring examples when converting the entered text in various ways.

Note
  • For details on prompt input and result value, please refer to Playground.
  • Recommendations when entering prompts
    • Please enter more than one pair of samples into the prompt for better accuracy.
    • When entering the contents for creating the result value, make sure no space at the end of the text.
  • The generated words and sentences are examples, and the generated sentences may vary each time when the prompt is executed.

Correct spellings

The following describes how to set parameters and configure prompts so that a given sentence can be parsed and converted into a correctly spelled sentence.

Set parameter

We recommend to set the parameters as follows.

Parameter Value
Maximum token 150 or lower
Temperature 0.3 or lower
Repetition penalty 3 or lower
Stop sequence ###↵, sentence:, correction:
Inject start text ↵correction:
Inject restart text ↵###↵sentence:

Configure prompt

Build the prompt as follows.

//You should enter directives to let the generator know the context of what you want.

The sentences entered will be changed to sentences corrected for incorrect grammar.

//Please provide sample sentences and corrections.

###
Sentence: You and them are different.
You can do in you're way.
Correction: You and they are different. You can do in your way.
###
Sentence: How do you behaves like this?
Correction: How do you behave like this?
###

//Please enter the sentence you want to correct.

Sentence: Is these okay now?

Result value

The result of executing the prompt is as follows.

The sentences entered will be changed to sentences corrected for incorrect grammar.

###
Sentence: You and them are different.
You can do in you're way.
Correction: You and they are different.
You can do in your way.
###
Sentence: How do you behaves like this?
Correction: How do you behave like this?
###

Sentence: Is these okay now?

//Result value

Correction: Is this okay now?

###
Sentence:

Product name corrector

The following describes how to set parameters and enter prompts so that a given sentence can be parsed and converted into a more concise form of name.

Set parameter

We recommend to set the parameters as follows.

Parameter Value
Maximum token 150 or lower
Temperature 0.3 or lower
Repetition penalty 3 or lower
Stop sequence ###↵, product name:, correction:
Inject start text ↵correction:
Inject restart text ↵###↵product name:

Configure prompt

Build the prompt as follows.

//You should enter directives to let the generator know the context of what you want.

Correct the product names entered briefly.

//Please provide sample product names and corrections.

Product name: Soap flower money roll tissue box reverse pocket money box carnation flower box parents’ birthday 60th birthday
Correction: Soap flower pocket money box
###
Product name: Golf wear women’s logo graphic T-shirts sleeveless summer half sleeves T-shirts
Correction: Golf wear women’s round neck T-shirt
###

//Please enter the sentence you want to correct.

Product name: Sportswear women’s pastel-colored fleece-lined leggings

Result value

The result of executing the prompt is as follows.

Correct the product names entered briefly.

Product name: Soap flower money roll tissue box reverse pocket money box carnation flower box parents’ birthday 60th birthday
Correction: Soap flower pocket money box
###
Product name: Golf wear women’s logo graphic T-shirts sleeveless summer half sleeves T-shirts
Correction: Golf wear women’s round neck T-shirt
###
Product name: Sportswear women’s pastel-colored fleece-lined leggings


//Result value
Correction: Sportswear women’s workout pants

###
Product name:

Stylistic transformation (dialect, historical drama tone, character tone, etc.)

The following describes how to set parameters and enter prompts so that a given sentence can be analyzed and converted into a specified tone.

Set parameter

We recommend to set the parameters as follows.

Parameter Value
Maximum token 150 or lower
Temperature 0.3 or lower
Repetition penalty 3 or lower
Stop sequence ###↵, sentence:, dialect:
Inject start text ↵dialect:
Inject restart text ↵###↵sentence:

Configure prompt

Build the prompt as follows.

//You should enter directives to let the generator know the context of what you want.

The sentences entered will be changed to dialect.

//Please provide sample sentences and transformed sentences.

Sentence: What are you talking about?
Dialect: Whaddaya talkin' 'bout?
###
Sentence: Why are you doing this?
Dialect: Why’re ya doin’ this?
###

//Please enter the sentence you want to transform.

Sentence: Are you going to come to school tomorrow?

Result value

The result of executing the prompt is as follows.

The sentences entered will be changed to dialect.

Sentence: What are you talking about?
Dialect: Whaddaya talkin' 'bout?
###
Sentence: Why are you doing this?
Dialect: Why’re ya doin’ this?
###
Sentence: Are you going to come to school tomorrow?

//Result value

Dialect: Are ya fixin' to come to school tomorrow?

###
Sentence:

Was this article helpful?