# Ensembling Factored Neural Machine Translation Models for Automatic Post-Editing and Quality Estimation

## TL;DR

This paper introduces an ensemble of neural machine translation models with input factors for improved automatic post-editing and quality estimation, achieving state-of-the-art results in both tasks.

## Contribution

It presents a novel ensemble approach combining specialized NMT models with input factors for APE and QE, unifying these tasks within a single framework.

## Key findings

- Achieved state-of-the-art results in APE and QE tasks.
- Ensemble models outperform individual models in accuracy.
- Input factors enhance the representation for better post-editing and estimation.

## Abstract

This work presents a novel approach to Automatic Post-Editing (APE) and Word-Level Quality Estimation (QE) using ensembles of specialized Neural Machine Translation (NMT) systems. Word-level features that have proven effective for QE are included as input factors, expanding the representation of the original source and the machine translation hypothesis, which are used to generate an automatically post-edited hypothesis. We train a suite of NMT models that use different input representations, but share the same output space. These models are then ensembled together, and tuned for both the APE and the QE task. We thus attempt to connect the state-of-the-art approaches to APE and QE within a single framework. Our models achieve state-of-the-art results in both tasks, with the only difference in the tuning step which learns weights for each component of the ensemble.