USCORE: An Effective Approach to Fully Unsupervised Evaluation Metrics for Machine Translation

TL;DR

USCORE introduces a fully unsupervised method for evaluating machine translation that leverages pseudo-parallel data and multilingual embeddings, outperforming supervised metrics on most datasets.

Contribution

The paper presents a novel fully unsupervised evaluation framework for machine translation, combining metric induction, pseudo-parallel data mining, and multilingual embeddings.

Findings

Outperforms supervised metrics on 4 out of 5 datasets

Develops an iterative process for remapping vector spaces

Induces unsupervised multilingual sentence embeddings

Abstract

The vast majority of evaluation metrics for machine translation are supervised, i.e., (i) are trained on human scores, (ii) assume the existence of reference translations, or (iii) leverage parallel data. This hinders their applicability to cases where such supervision signals are not available. In this work, we develop fully unsupervised evaluation metrics. To do so, we leverage similarities and synergies between evaluation metric induction, parallel corpus mining, and MT systems. In particular, we use an unsupervised evaluation metric to mine pseudo-parallel data, which we use to remap deficient underlying vector spaces (in an iterative manner) and to induce an unsupervised MT system, which then provides pseudo-references as an additional component in the metric. Finally, we also induce unsupervised multilingual sentence embeddings from pseudo-parallel data. We show that our fully unsupervised metrics are effective, i.e., they beat supervised competitors on 4 out of our 5 evaluation datasets. We make our code publicly available.