Papers › HIT-SCIR at MRP 2019: A Unified Pipeline for Meaning Representation Parsing via...

HIT-SCIR at MRP 2019: A Unified Pipeline for Meaning Representation Parsing via Efficient Training and Effective Encoding

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

Wanxiang Che, Longxu Dou, Yang Xu, Yuxuan Wang, Yijia Liu, Ting Liu

This paper describes our system (HIT-SCIR) for CoNLL 2019 shared task: Cross-Framework Meaning Representation Parsing. We extended the basic transition-based parser with two improvements: a) Efficient Training by realizing Stack LSTM parallel training; b) Effective Encoding via adopting deep contextualized word embeddings BERT. Generally, we proposed a unified pipeline to meaning representation parsing, including framework-specific transition-based parsers, BERT-enhanced word representation, and post-processing. In the final evaluation, our system was ranked first according to ALL-F1 (86.2{\%}) and especially ranked first in UCCA framework (81.67{\%}).

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

UCCA ParsingWord Embeddings

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
UCCA Parsing CoNLL 2019 Transition-based (+BERT + Efficient Training + Effective Encoding) Full MRP F1 81.7 #1 of 3 Archive leaderboard report
UCCA Parsing CoNLL 2019 Transition-based (+BERT + Efficient Training + Effective Encoding) Full UCCA F1 66.7 #1 of 3 Archive leaderboard report
UCCA Parsing CoNLL 2019 Transition-based (+BERT + Efficient Training + Effective Encoding) LPP MRP F1 82.6 #1 of 3 Archive leaderboard report
UCCA Parsing CoNLL 2019 Transition-based (+BERT + Efficient Training + Effective Encoding) LPP UCCA F1 64.4 #1 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 DropoutBERTDense 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