Title: Translate Smart, not Hard: Cascaded Translation Systems with Quality-Aware Deferral
Authors: António Farinhas, Nuno M. Guerreiro, Sweta Agrawal, Ricardo Rei, André F. T. Martins
Published: 18th February 2025 (Tuesday) @ 10:05:40
Link: http://arxiv.org/abs/2502.12701v1
Abstract
Larger models often outperform smaller ones but come with high computational costs. Cascading offers a potential solution. By default, it uses smaller models and defers only some instances to larger, more powerful models. However, designing effective deferral rules remains a challenge. In this paper, we propose a simple yet effective approach for machine translation, using existing quality estimation (QE) metrics as deferral rules. We show that QE-based deferral allows a cascaded system to match the performance of a larger model while invoking it for a small fraction (30% to 50%) of the examples, significantly reducing computational costs. We validate this approach through both automatic and human evaluation.