论文标题
更糟糕的是，但是BLEU更好？在多任务端到端语音翻译中，利用单词嵌入为中级
Worse WER, but Better BLEU? Leveraging Word Embedding as Intermediate in Multitask End-to-End Speech Translation
论文作者
论文摘要
语音翻译（ST）旨在学习从源语言中的语音转变到目标语言的文本。先前的作品表明，多任务学习改善了ST性能，其中识别解码器会生成源语言的文本，而翻译解码器根据识别解码器的输出获得了最终翻译。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重要，我们建议通过利用嵌入单词嵌入为中级来改善多任务st模型。
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.
