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 2007.11648cs.CL
收藏

语言相关性对基于母语的语言模型中跨语言迁移学习的影响

Effects of Language Relatedness for Cross-lingual Transfer Learning in Character-Based Language Models

Aalto University(阿尔托大学);Helsinki University(赫尔辛基大学);Inscripta(Inscripta公司)

Mittul Singh, Peter Smit, Sami Virpioja, Mikko Kurimo

摘要:

与基于多字符单元的神经网络语言模型相比,基于神经网络的神经网络语言模型(NNLM)具有更小的词汇量和更快的训练时间的优势。然而,在低资源的情况下,字符和多字符NNLM遭受数据稀疏。在这种情况下,跨语言迁移通过允许从源语言到目标语言的信息迁移,提高了多字符NNLM的性能。同样,我们建议使用跨语言迁移的字符NNLM应用于低资源的自动语音识别(ASR)。然而,将跨语言迁移应用于字符NNLM并不那么简单。我们观察到源语言的相关性在字符NNLM的跨语言预训练中起着重要的作用。我们评估这方面的ASR任务的两个目标语言:芬兰语(英语和爱沙尼亚语作为源)和瑞典语(丹麦语,挪威语和英语作为源)。先前的工作没有观察到使用相关或不相关的语言多字符NNLM之间的差异。然而,我们表明,对于基于字符的NNLM,只有使用相关语言进行预训练才能提高ASR性能,使用不相关的语言可能会使其恶化。我们还观察到,当目标数据比源数据少得多时,好处更大。

英文摘要:

Character-based Neural Network Language Models (NNLM) have the advantage of smaller vocabulary and thus faster training times in comparison to NNLMs based on multi-character units. However, in low-resource scenarios, both the character and multi-character NNLMs suffer from data sparsity. In such scenarios, cross-lingual transfer has improved multi-character NNLM performance by allowing information transfer from a source to the target language. In the same vein, we propose to use cross-lingual transfer for character NNLMs applied to low-resource Automatic Speech Recognition (ASR). However, applying cross-lingual transfer to character NNLMs is not as straightforward. We observe that relatedness of the source language plays an important role in cross-lingual pretraining of character NNLMs. We evaluate this aspect on ASR tasks for two target languages: Finnish (with English and Estonian as source) and Swedish (with Danish, Norwegian, and English as source). Prior work has observed no difference between using the related or unrelated language for multi-character NNLMs. We, however, show that for character-based NNLMs, only pretraining with a related language improves the ASR performance, and using an unrelated language may deteriorate it. We also observe that the benefits are larger when there is much lesser target data than source data.

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。

↑