We present an error analysis of neural UPOS taggers to evaluate why using
gold standard tags has such a large positive contribution to parsing
performance while using predicted UPOS tags either harms performance or offers
a negligible improvement. We evaluate what neural dependency parsers implicitly
learn about word types and how this relates to the errors taggers make to
explain the minimal impact using predicted tags has on parsers. We also present
a short analysis on what contexts result in reductions in tagging performance.
We then mask UPOS tags based on errors made by taggers to tease away the
contribution of UPOS tags which taggers succeed and fail to classify correctly
and the impact of tagging errors.

通过错误分析神经 UPOS 标签器，我们评估了为什么使用黄金标准标签对于解析性能有很大的积极贡献，而使用预测的 UPOS 标签要么损害性能，要么提供微不足道的改进。我们评估了神经依赖分析器隐含地学习了哪些单词类型，以及这与标记器产生的错误有何关系，以解释使用预测标签对解析器几乎没有影响的原因。同时，我们还对导致标记性能降低的上下文进行了简短分析，然后基于标记器的错误屏蔽了 UPOS 标签，以分离标记器正确分类和错误分类的 UPOS 标签的贡献以及标记错误的影响。

标注器无法学习的，解析器最需要的

What Taggers Fail to Learn, Parsers Need the Most

We present the system submission from the FASTPARSE team for the EUD Shared
Task at IWPT 2020. We engaged with the task by focusing on efficiency. For this
we considered training costs and inference efficiency. Our models are a
combination of distilled neural dependency parsers and a rule-based system that
projects UD trees into EUD graphs. We obtained an average ELAS of 74.04 for our
official submission, ranking 4th overall.

FASTPARSE 团队针对 IWPT2020 的 EUD Shared Task 提出一种训练和推理效率结合的模型，结合神经依存解析和基于规则的系统，将 UD 树映射为 EUD 图，在官方提交中获得 74.04 的平均 ELAS，排名第 4。