TUPA at MRP 2019: A Multi-Task Baseline System

CONLL 2019  ·  Daniel Hershcovich, Ofir Arviv ·

This paper describes the TUPA system submission to the shared task on Cross-Framework Meaning Representation Parsing (MRP) at the 2019 Conference for Computational Language Learning (CoNLL). Because it was prepared by one of the task co-organizers, TUPA provides a baseline point of comparison and is not considered in the official ranking of participating systems. While originally developed for UCCA only, TUPA has been generalized to support all MRP frameworks included in the task, and trained using multi-task learning to parse them all with a shared model. It is a transition-based parser with a BiLSTM encoder, augmented with BERT contextualized embeddings.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
UCCA Parsing CoNLL 2019 Transition-based (+BERT + MTL) Full UCCA F1 35.6 # 3
Full MRP F1 64.1 # 3
LPP UCCA F1 50.3 # 3
LPP MRP F1 73.1 # 3
UCCA Parsing CoNLL 2019 Transition-based (+BERT) Full UCCA F1 57.4 # 2
Full MRP F1 77.7 # 2
LPP UCCA F1 65.9 # 1
LPP MRP F1 82.2 # 2

Methods