The True Score of Statistical Paraphrase Generation

This article delves into the scoring function of the statistical paraphrase generation model. It presents an algorithm for exact computation and two applicative experiments. The first experiment analyses the behaviour of a statistical paraphrase generation decoder, and raises some issues with the ordering of n-best outputs. The second experiment shows that a major boost of performance can be obtained by embedding a true score computation inside a Monte-Carlo sampling based paraphrase generator.