arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.08595cs.CLcs.SDeess.AS
收藏

用于同时机器翻译的有效Wait-k模型

Efficient Wait-k Models for Simultaneous Machine Translation

CNRS(法国国家科学研究中心);Grenoble INP(格勒诺布尔国立理工学院);Inria(法国国家信息与自动化研究所);LIG(格勒诺布尔信息学实验室);LJK(让·昆特曼实验室);Facebook AI Research(脸书人工智能研究院)

Maha Elbayad, Laurent Besacier, Jakob Verbeek

摘要:

同步机器翻译包括在整个输入序列可用之前开始输出生成。Wait-k解码器为这个问题提供了一种简单但有效的方法。它们首先读取k个源令牌,然后在生成目标令牌和读取另一个源令牌之间交替。我们调查的行为wait-k解码在低资源设置口语语料库使用IWITOS数据集。我们使用单向编码器改进了这些模型的训练,并在多个k值上进行训练。使用Transformer和2D卷积架构的实验表明,我们的wait-k模型在广泛的延迟级别上具有良好的泛化能力。我们还表明,2D卷积架构是有竞争力的Transformers的口语同步翻译。

英文摘要:

Simultaneous machine translation consists in starting output generation before the entire input sequence is available. Wait-k decoders offer a simple but efficient approach for this problem. They first read k source tokens, after which they alternate between producing a target token and reading another source token. We investigate the behavior of wait-k decoding in low resource settings for spoken corpora using IWSLT datasets. We improve training of these models using unidirectional encoders, and training across multiple values of k. Experiments with Transformer and 2D-convolutional architectures show that our wait-k models generalize well across a wide range of latency levels. We also show that the 2D-convolution architecture is competitive with Transformers for simultaneous translation of spoken language.

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。

↑