Efficient EUD Parsing
This work addresses efficiency in parsing for natural language processing, but it is incremental as it builds on existing methods.
The authors tackled the EUD parsing task by focusing on efficiency in both training and inference, combining distilled neural dependency parsers with a rule-based system to project UD trees into EUD graphs, achieving an average ELAS of 74.04 and ranking 4th overall.
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.