We demonstrate that replacing an LSTM encoder with a self-attentive
architecture can lead to improvements to a state-of-the-art discriminative
constituency parser. The use of attention makes explicit the manner in which
information is propagated between different locations in the sente
本研究提出了标签关注层,一种新的自注意形式,其中关注头表示标签。运行实验并在 Penn Treebank(PTB)和中文 Treebank 上展示出其在词法句法分析方面的最新成果,标签关注层在该实验中表现出了更好的性能,相比现有工作需要较少的自我注意层数。最后,我们发现标签注意头学习了语法类别之间的关系,并显示了分析错误的路径。