# Splitting EUD graphs into trees: A quick and clatty approach

arXiv: https://arxiv.org/abs/2106.13155 · HTML: https://mlsanity.com/paper/2106.13155/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 24 Jun 2021.

## Builds on (most cited first, 9 of 9)

- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Viable Dependency Parsing as Sequence Labeling](https://mlsanity.com/paper/1902.10505/) (2019)
- [Constituent Parsing as Sequence Labeling](https://mlsanity.com/paper/1810.08994/) (2018)
- [Bracketing Encodings for 2-Planar Dependency Parsing](https://mlsanity.com/paper/2011.00596/) (2020)
- [Parsing All: Syntax and Semantics, Dependencies and Spans](https://mlsanity.com/paper/1908.11522/) (2019)
- [Sequence Labeling Parsing by Learning Across Representations](https://mlsanity.com/paper/1907.01339/) (2019)
- [A Modest Pareto Optimisation Analysis of Dependency Parsers in 2021](https://mlsanity.com/paper/2106.04216/) (2021)
- [Efficient EUD Parsing](https://mlsanity.com/paper/2006.00838/) (2020)
- [A Dynamic Oracle for Linear-Time 2-Planar Dependency Parsing](https://mlsanity.com/paper/1805.05202/) (2018)

## Built on by (most cited first, 1 of 1)

- [Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments](https://mlsanity.com/paper/2110.06865/) (2021)

## Abstract (arXiv)

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.