arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.07575cs.CLeess.AS
收藏

弥合端到端语音翻译的预训练和微调之间的差距

Bridging the Gap between Pre-Training and Fine-Tuning for End-to-End Speech Translation

Nankai University(南开大学)

Chengyi Wang, Yu Wu, Shujie Liu, Zhenglu Yang, Ming Zhou

摘要:

端到端语音翻译是近年来的一个热门话题,其目的是通过端到端的模式将一段音频翻译成一种特定的语言。传统的方法采用多任务学习和预训练方法来完成这项任务,但它们受到预训练和微调之间的巨大差距的影响。为了解决这些问题,我们提出了一个串联连接编码网络(TCEN),它通过在微调中重复使用所有连接,保持连接的角色一致,并预先训练注意力模块来弥合差距。此外,我们提出了两个简单而有效的方法来保证语音编码器的输出和MT编码器的输入是一致的语义表示和序列长度。实验结果表明,我们的模型在大型基准数据集上的性能优于基线2.2 BLEU。

英文摘要:

End-to-end speech translation, a hot topic in recent years, aims to translate a segment of audio into a specific language with an end-to-end model. Conventional approaches employ multi-task learning and pre-training methods for this task, but they suffer from the huge gap between pre-training and fine-tuning. To address these issues, we propose a Tandem Connectionist Encoding Network (TCEN) which bridges the gap by reusing all subnets in fine-tuning, keeping the roles of subnets consistent, and pre-training the attention module. Furthermore, we propose two simple but effective methods to guarantee the speech encoder outputs and the MT encoder inputs are consistent in terms of semantic representation and sequence length. Experimental results show that our model outperforms baselines 2.2 BLEU on a large benchmark dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑