Different languages might have different word orders. In this paper, we
investigate cross-lingual transfer and posit that an order-agnostic model will
perform better when transferring to distant foreign languages. To test our
hypothesis, we train dependency parsers on an English corpus and evaluate their
transfer performance on 30 other languages. Specifically, we compare encoders
and decoders based on Recurrent Neural Networks (RNNs) and modified
self-attentive architectures. The former relies on sequential information while
the latter is more flexible at modeling word order. Rigorous experiments and
detailed analysis shows that RNN-based architectures transfer well to languages
that are close to English, while self-attentive models have better overall
cross-lingual transferability and perform especially well on distant languages.

本文研究不同语言的词序，并假设一个与词序无关的模型将在转移到远程外语时表现更好。通过在英语语料库上训练依赖解析器，并在 30 种其他语言上评估它们的转移性能，我们比较基于递归神经网络（RNN）和修改的自我注意体系结构的编码器和解码器。严格的实验和详细的分析表明，基于 RNN 的架构在传输到接近英语的语言时表现良好，而自我注意的模型具有更好的整体跨语言可转移性并在远程语言上表现特别好。