Papers › TUPA at MRP 2019: A Multi-Task Baseline System

TUPA at MRP 2019: A Multi-Task Baseline System

1 Nov 2019CONLL 2019 11archive 2025-07-28

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.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Multi-Task LearningUCCA Parsing

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
UCCA Parsing CoNLL 2019 Transition-based (+BERT) Full MRP F1 77.7 #2 of 3 Archive leaderboard report
UCCA Parsing CoNLL 2019 Transition-based (+BERT) Full UCCA F1 57.4 #2 of 3 Archive leaderboard report
UCCA Parsing CoNLL 2019 Transition-based (+BERT) LPP MRP F1 82.2 #2 of 3 Archive leaderboard report
UCCA Parsing CoNLL 2019 Transition-based (+BERT) LPP UCCA F1 65.9 #2 of 3 Archive leaderboard report
UCCA Parsing CoNLL 2019 Transition-based (+BERT + MTL) Full MRP F1 64.1 #3 of 3 Archive leaderboard report
UCCA Parsing CoNLL 2019 Transition-based (+BERT + MTL) Full UCCA F1 35.6 #3 of 3 Archive leaderboard report
UCCA Parsing CoNLL 2019 Transition-based (+BERT + MTL) LPP MRP F1 73.1 #3 of 3 Archive leaderboard report
UCCA Parsing CoNLL 2019 Transition-based (+BERT + MTL) LPP UCCA F1 50.3 #3 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdamAttentionAttention DropoutBERTBiLSTMDense ConnectionsDropoutLSTMLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSigmoid ActivationSoftmaxTanh ActivationWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections