We present the system submission from the FASTPARSE team for the EUD Shared Task at IWPT 2021. We engaged in the task last year by focusing on efficiency. This year we have focused on experimenting with new ideas on a limited time budget. Our system is based on splitting the EUD graph into several trees, based on linguistic criteria. We predict these trees using a sequence-labelling parser and combine them into an EUD graph. The results were relatively poor, although not a total disaster and could probably be improved with some polishing of the system's rough edges.
翻译:我们介绍了FASTPARSE团队在IWPT 2021 EUD 共有任务中提交的系统文件。我们去年的工作重点是效率。我们今年的工作重点是对有限时间预算的新想法进行实验。我们的系统基于语言标准,将EUD图分为几棵树。我们用一个序列标签解析器预测这些树,并将它们合并成EUD 图表。结果相对较差,虽然不是完全的灾难,而且也许可以通过对系统粗糙的边缘进行一些擦拭来改进。