deeplearning

deeplearning / bert_paraphrase / 1.0.0

README.md

Overview

This algorithm uses the bert-base-cased model to determine if a sentence is paraphrased or not.

Usage

Input

ParameterDescription
sentence_0The main sentence to compare against
sentence_1The first sentence to compare against the main sentence
sentence_2The second sentence to compare against the main sentence

Output

ParameterDescription
comparison_1Comparing the first sentence against the main sentence
comparison_2Comparing the second sentence against the main sentence

Examples

Example 1.

  • Parameter 1: Main sentence to compare against
  • Parameter 2: First sentence for comparison
  • Parameter 3: Second sentence for comparison

Input:

{
	"sentence_0": "This research was consistent with his findings.",
	"sentence_1": "His findings were compatible with this research.",
	"sentence_2": "His findings were not compatible with this research."
}

Output:

{
  "comparison_1": "sentence_1 is a paraphrase of sentence_0",
  "comparison_2": "sentence_2 is a paraphrase of sentence_0"
}