\'UFAL MRPipe at MRP 2019: UDPipe Goes Semantic in the Meaning Representation Parsing Shared Task

TL;DR

This paper describes a novel, framework-agnostic neural network system for semantic parsing across multiple meaning representation frameworks, achieving third place in the CoNLL 2019 shared task.

Contribution

It introduces a uniform graph-to-graph neural network architecture that operates without prior knowledge of graph structures, extending UDPipe 2.0 for semantic parsing.

Findings

Achieved third place in MRP 2019 shared task

Proposed a framework-agnostic neural architecture

Demonstrated effective implicit modeling of meaning graphs

Abstract

We present a system description of our contribution to the CoNLL 2019 shared task, Cross-Framework Meaning Representation Parsing (MRP 2019). The proposed architecture is our first attempt towards a semantic parsing extension of the UDPipe 2.0, a lemmatization, POS tagging and dependency parsing pipeline. For the MRP 2019, which features five formally and linguistically different approaches to meaning representation (DM, PSD, EDS, UCCA and AMR), we propose a uniform, language and framework agnostic graph-to-graph neural network architecture. Without any knowledge about the graph structure, and specifically without any linguistically or framework motivated features, our system implicitly models the meaning representation graphs. After fixing a human error (we used earlier incorrect version of provided test set analyses), our submission would score third in the competition evaluation. The source code of our system is available at https://github.com/ufal/mrpipe-conll2019.