论文标题
联合语音翻译和命名实体识别
Joint Speech Translation and Named Entity Recognition
论文作者
论文摘要
现代自动翻译系统通过提供上下文支持和知识来瞄准将人类放置在中心的位置。在这种情况下，一项关键任务是通过有关上述实体的信息丰富了输出，目前正在实现使用命名实体识别（NER）和实体链接系统处理生成的翻译。鉴于直接语音翻译（ST）模型以及级联反应的已知弱点（误差传播和额外潜伏期）所显示的最新有希望的结果，在本文中，我们提出了共同执行ST和NER的多任务模型，并将它们与级联基线进行比较。实验结果表明，我们的模型在NER任务（0.4-1.0 F1）上的表现显着超过了级联，而在翻译质量方面没有降解，并且具有与普通直接ST模型相同的计算效率。
Modern automatic translation systems aim at place the human at the center by providing contextual support and knowledge. In this context, a critical task is enriching the output with information regarding the mentioned entities, which is currently achieved processing the generated translation with named entity recognition (NER) and entity linking systems. In light of the recent promising results shown by direct speech translation (ST) models and the known weaknesses of cascades (error propagation and additional latency), in this paper we propose multitask models that jointly perform ST and NER, and compare them with a cascade baseline. The experimental results show that our models significantly outperform the cascade on the NER task (by 0.4-1.0 F1), without degradation in terms of translation quality, and with the same computational efficiency of a plain direct ST model.
