This work visits the topic of jointly parsing constituency and dependency trees, i.e., to produce compatible constituency and dependency trees simultaneously for input sentences, which is attractive considering that the two types of trees are complementary in representing syntax. Compared with previous works, we make progress in four aspects: (1) adopting a much more efficient decoding algorithm, (2) exploring joint modeling at the training phase, instead of only at the inference phase, (3) proposing high-order scoring components for constituent-dependency interaction, (4) gaining more insights via in-depth experiments and analysis.

翻译：本研究重新审视了联合解析成分树和依存树这一课题，即同时为输入句子生成兼容的成分树和依存树。考虑到这两种树在句法表示上具有互补性，该任务颇具吸引力。与以往工作相比，我们在四个方面取得了进展：（1）采用更高效的解码算法；（2）探索在训练阶段而非仅在推理阶段进行联合建模；（3）提出用于成分-依存交互的高阶评分组件；（4）通过深入的实验与分析获得更多洞见。