Hitachi at MRP 2020: Text-to-Graph-Notation Transducer

Hiroaki Ozaki, Gaku Morio, Yuta Koreeda, Terufumi Morishita, Toshinori Miyoshi


Abstract
This paper presents our proposed parser for the shared task on Meaning Representation Parsing (MRP 2020) at CoNLL, where participant systems were required to parse five types of graphs in different languages. We propose to unify these tasks as a text-to-graph-notation transduction in which we convert an input text into a graph notation. To this end, we designed a novel Plain Graph Notation (PGN) that handles various graphs universally. Then, our parser predicts a PGN-based sequence by leveraging Transformers and biaffine attentions. Notably, our parser can handle any PGN-formatted graphs with fewer framework-specific modifications. As a result, ensemble versions of the parser tied for 1st place in both cross-framework and cross-lingual tracks.
Anthology ID:
2020.conll-shared.4
Volume:
Proceedings of the CoNLL 2020 Shared Task: Cross-Framework Meaning Representation Parsing
Month:
November
Year:
2020
Address:
Online
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
40–52
Language:
URL:
https://www.aclweb.org/anthology/2020.conll-shared.4
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.conll-shared.4.pdf