Automatic Quality Estimation for Natural Language Generation: Ranting (Jointly Rating and Ranking)

TL;DR

This paper introduces a recurrent neural network system for automatic quality estimation of NLG outputs that jointly learns to rate and rank outputs, improving correlation with human judgments and achieving state-of-the-art results.

Contribution

It presents a novel joint rating and ranking neural network model that leverages synthetic data and learning to rank techniques for enhanced quality estimation in NLG.

Findings

12% increase in correlation with human ratings

4% accuracy improvement on the E2E dataset

State-of-the-art ranking performance

Abstract

We present a recurrent neural network based system for automatic quality estimation of natural language generation (NLG) outputs, which jointly learns to assign numerical ratings to individual outputs and to provide pairwise rankings of two different outputs. The latter is trained using pairwise hinge loss over scores from two copies of the rating network. We use learning to rank and synthetic data to improve the quality of ratings assigned by our system: we synthesise training pairs of distorted system outputs and train the system to rank the less distorted one higher. This leads to a 12% increase in correlation with human ratings over the previous benchmark. We also establish the state of the art on the dataset of relative rankings from the E2E NLG Challenge (Du\v{s}ek et al., 2019), where synthetic data lead to a 4% accuracy increase over the base model.