arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.03320cs.CLeess.AS
收藏

一对多多语言端到端语音翻译

One-To-Many Multilingual End-to-end Speech Translation

Fondazione Bruno Kessler(布鲁诺·凯斯勒基金会);University of Trento(特伦托大学)

Mattia Antonino Di Gangi, Matteo Negri, Marco Turchi

摘要:

如今,训练用于口语翻译(口语翻译)的端到端神经模型仍然必须面对极端的数据稀缺条件。与自动语音识别(ASR)和机器翻译(MT)等密切相关的任务相比,现有的并行语料库确实小了几个数量级,这些任务通常包括数千万个实例。为了应对数据匮乏,在本文中,我们探讨了迁移学习在端到端的学习任务的多语言方法的有效性。多语言解决方案在机器翻译中得到了广泛的研究,通常依赖于"\textit{target forcing}“,其中多语言并行数据通过在输入序列前添加指定目标语言的语言标记来组合以训练单个模型。然而,当在语音翻译中进行测试时,我们的实验表明,MT类\textit{target forcing},按原样使用,是不能有效地区分目标语言。因此,我们提出了一个变体,使用目标语言嵌入来根据语言在空间的不同部分中移动输入表示,以便更好地支持所需目标语言的输出。我们对从英语到六种语言的端到端翻译的实验表明,在翻译成类似语言时,特别是在这些数据不足的情况下,有了重要的改进。当使用英语ASR数据作为附加语言(最高达$+2.5$ BLEU点)时,可获得进一步的改进。

英文摘要:

Nowadays, training end-to-end neural models for spoken language translation (SLT) still has to confront with extreme data scarcity conditions. The existing SLT parallel corpora are indeed orders of magnitude smaller than those available for the closely related tasks of automatic speech recognition (ASR) and machine translation (MT), which usually comprise tens of millions of instances. To cope with data paucity, in this paper we explore the effectiveness of transfer learning in end-to-end SLT by presenting a multilingual approach to the task. Multilingual solutions are widely studied in MT and usually rely on ``\textit{target forcing}'', in which multilingual parallel data are combined to train a single model by prepending to the input sequences a language token that specifies the target language. However, when tested in speech translation, our experiments show that MT-like \textit{target forcing}, used as is, is not effective in discriminating among the target languages. Thus, we propose a variant that uses target-language embeddings to shift the input representations in different portions of the space according to the language, so to better support the production of output in the desired target language. Our experiments on end-to-end SLT from English into six languages show important improvements when translating into similar languages, especially when these are supported by scarce data. Further improvements are obtained when using English ASR data as an additional language (up to $+2.5$ BLEU points).

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。

↑