The usefulness of part-of-speech tags for parsing has been heavily questioned due to the success of word-contextualized parsers. Yet, most studies are limited to coarse-grained tags and high quality written content; while we know little about their influence when it comes to models in production that face lexical errors. We expand these setups and design an adversarial attack to verify if the use of morphological information by parsers: (i) contributes to error propagation or (ii) if on the other hand it can play a role to correct mistakes that word-only neural parsers make. The results on 14 diverse UD treebanks show that under such attacks, for transition- and graph-based models their use contributes to degrade the performance even faster, while for the (lower-performing) sequence labeling parsers they are helpful. We also show that if morphological tags were utopically robust against lexical perturbations, they would be able to correct parsing mistakes.

翻译：词性标注对句法分析的实用性因基于上下文的词嵌入解析器的成功而备受质疑。然而，多数研究局限于粗粒度标签与高质量书面内容，鲜少探讨其在面对词汇错误的实际生产模型中的影响。我们扩展了这些研究框架，设计了一种对抗性攻击，以验证解析器使用形态信息是否：(i) 导致错误传播，或 (ii) 反而有助于纠正纯词汇神经网络解析器的错误。在14个多样化的UD树库上的实验结果表明，对于基于转移和基于图的解析器，此类攻击会使其性能加速下降；而对于（性能较低的）序列标注解析器，形态信息则具有辅助作用。此外，我们证明：若形态标签能理想地抵御词汇扰动，则可有效纠正句法分析错误。