ÚFAL MRPipe at MRP 2019: UDPipe Goes Semantic in the Meaning Representation Parsing Shared Task

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10405605" target="_blank" >RIV/00216208:11320/19:10405605 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.aclweb.org/anthology/K19-2012/" target="_blank" >https://www.aclweb.org/anthology/K19-2012/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/K19-2012" target="_blank" >10.18653/v1/K19-2012</a>

Jazyk výsledku

angličtina

Název v původním jazyce

ÚFAL MRPipe at MRP 2019: UDPipe Goes Semantic in the Meaning Representation Parsing Shared Task

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

ÚFAL MRPipe at MRP 2019: UDPipe Goes Semantic in the Meaning Representation Parsing Shared Task

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the CoNLL 2019 Shared Task: Cross-Framework Meaning Representation Parsing

ISBN

978-1-950737-60-4

ISSN

—

e-ISSN

—

Počet stran výsledku

11

Strana od-do

127-137

Název nakladatele

Association for Computational Linguistics

Místo vydání

Stroudsburg, PA, USA

Místo konání akce

Hong Kong, China

Datum konání akce

3. 11. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—