更坏的WER，但更好的BLEU？在多任务端到端语音翻译中利用单词嵌入作为中介（CS CL）---刘子蔚

语音翻译（ST）旨在学习从源语言中的语音到目标语言中的文本的转换。先前的工作表明，多任务学习提高了ST性能，其中识别解码器生成源语言的文本，翻译解码器根据识别解码器的输出获得最终翻译。因为识别解码器的输出是否具有正确的语义比其准确性更为关键，所以我们建议通过使用词嵌入作为中介来改进多任务ST模型。

原文标题：Worse WER, but Better BLEU? Leveraging Word Embedding as Intermediate in Multitask End-to-End Speech Translation

原文：Speech translation (ST) aims to learn transformations from speech in the source language to the text in the target language. Previous works show that multitask learning improves the ST performance, in which the recognition decoder generates the text of the source language, and the translation decoder obtains the final translations based on the output of the recognition decoder. Because whether the output of the recognition decoder has the correct semantics is more critical than its accuracy, we propose to improve the multitask ST model by utilizing word embedding as the intermediate.

原文作者：Shun-Po Chuang, Tzu-Wei Sung, Alexander H. Liu, Hung-yi Lee

原文地址：https://arxiv.org/abs/2005.10678