Contextual word representations derived from pre-trained bidirectional language models (biLMs) have recently been shown to provide significant improvements to the state of the art for a wide range of NLP tasks. However, many questions remain as to how and why these models are so effective. In this paper, we present a detailed empirical study of how the choice of neural architecture (e.g. LSTM, CNN, or self attention) influences both end task accuracy and qualitative properties of the representations that are learned. We show there is a tradeoff between speed and accuracy, but all architectures learn high quality contextual representations that outperform word embeddings for four challenging NLP tasks. Additionally, all architectures learn representations that vary with network depth, from exclusively morphological based at the word embedding layer through local syntax based in the lower contextual layers to longer range semantics such coreference at the upper layers. Together, these results suggest that unsupervised biLMs, independent of architecture, are learning much more about the structure of language than previously appreciated.

本文通过详细的实证研究探讨了神经网络模型架构（如：LSTM、CNN或自我注意力）对端到端NLP任务准确性和语言表示质量影响的权衡，研究结果表明预训练的双向语言模型可以学习到关于语言结构比以往认为的更多，无论采用何种架构，都是学习到高质量的上下文表示。

上下文词嵌入的解析：架构和表示