Splitting EUD graphs into trees: A quick and clatty approach

06/24/2021
by   Mark Anderson, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/01/2020

Efficient EUD Parsing

We present the system submission from the FASTPARSE team for the EUD Sha...
research
10/04/2022

Rainbow spanning trees in randomly coloured G_k-out

Given a graph G=(V,E) on n vertices and an assignment of colours to its ...
research
07/14/2021

TGIF: Tree-Graph Integrated-Format Parser for Enhanced UD with Two-Stage Generic- to Individual-Language Finetuning

We present our contribution to the IWPT 2021 shared task on parsing into...
research
04/17/2021

Question Decomposition with Dependency Graphs

QDMR is a meaning representation for complex questions, which decomposes...
research
08/23/2022

Even vertex ζ-graceful labeling on Rough Graph

Rough graph is the graphical structure of information system with imprec...
research
06/01/2021

Replicating and Extending "Because Their Treebanks Leak": Graph Isomorphism, Covariants, and Parser Performance

Søgaard (2020) obtained results suggesting the fraction of trees occurri...
research
05/12/2020

Deep Learning: Our Miraculous Year 1990-1991

In 2020, we will celebrate that many of the basic ideas behind the deep ...

Please sign up or login with your details

Forgot password? Click here to reset