We introduce polyglot language models, recurrent neural network models
trained to predict symbol sequences in many different languages using shared
representations of symbols and conditioning on typological information about
the language to be predicted. We apply these to the problem of modeling phone
sequences---a domain in which universal symbol inventories and
cross-linguistically shared feature representations are a natural fit.
Intrinsic evaluation on held-out perplexity, qualitative analysis of the
learned representations, and extrinsic evaluation in two downstream
applications that make use of phonetic features show (i) that polyglot models
better generalize to held-out data than comparable monolingual models and (ii)
that polyglot phonetic feature representations are of higher quality than those
learned monolingually.

通过应用多语言情境下的共用符号表示和语言的语言信息来训练递归神经网络模型，我们介绍了多语言模型的思想，以解决建模音序列的问题，该问题中具有普遍符号发明和跨语言共享特征表示。实验结果表明，多语言模型比单语言模型具有更好的泛化性能和更高质量的语音特征表示。