Multilingual neural machine translation (MNMT) aims to build a unified model for many language directions. Existing monolithic models for MNMT encounter two challenges: parameter interference among languages and inefficient inference for large models. In this paper, we revisit the classic multi-way structures and develop a detachable model by assigning each language (or group of languages) to an individual branch that supports plug-and-play training and inference. To address the needs of learning representations for all languages in a unified space, we propose a novel efficient training recipe, upon which we build an effective detachable model, Lego-MT. For a fair comparison, we collect data from OPUS and build a translation benchmark covering 433 languages and 1.3B parallel data. Experiments show that Lego-MT with 1.2B parameters brings an average gain of 3.2 spBLEU. It even outperforms M2M-100 with 12B parameters. The proposed training recipe brings a 28.2$\times$ speedup over the conventional multi-way training method.\footnote{ \url{https://github.com/CONE-MT/Lego-MT}.}

翻译：多语言神经机器翻译旨在构建一个统一模型来支持多种语言方向。现有用于多语言神经机器翻译的整体式模型面临两大挑战：语言间参数干扰以及大型模型的低效推理。本文重新审视经典的多分支结构，通过为每种语言（或语言组）分配独立分支，开发了一种支持即插即用训练与推理的可分离模型。为满足在统一空间中学习所有语言表示的需求，我们提出了一种新颖的高效训练方案，并在此基础上构建了有效的可分离模型Lego-MT。为进行公平比较，我们从OPUS收集数据并构建了一个覆盖433种语言、包含13亿平行语料的翻译基准。实验表明，参数量为12亿的Lego-MT平均提升3.2个spBLEU分数，甚至超越了参数量为120亿的M2M-100模型。所提出的训练方案相比传统多分支训练方法实现了28.2倍的加速。\footnote{\url{https://github.com/CONE-MT/Lego-MT}.}