Papers › Second-Order Neural Dependency Parsing with Message Passing and End-to-End Training

Second-Order Neural Dependency Parsing with Message Passing and End-to-End Training

10 Oct 2020Asian Chapter of the Association for Computational Linguistics 2020arXiv:2010.05003archive 2025-07-28

Xinyu Wang, Kewei Tu

In this paper, we propose second-order graph-based neural dependency parsing using message passing and end-to-end neural networks. We empirically show that our approaches match the accuracy of very recent state-of-the-art second-order graph-based neural dependency parsers and have significantly faster speed in both training and testing. We also empirically show the advantage of second-order parsing over first-order parsing and observe that the usefulness of the head-selection structured constraint vanishes when using BERT embedding.

Paper PDF Conference PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

wangxinyu0922/Second_Order_Parsing officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

Dependency Parsing

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Dependency Parsing	Chinese Treebank	MFVI	LAS	91.69	#1 of 1	Archive leaderboard	report
Dependency Parsing	Chinese Treebank	MFVI	UAS	92.78	#1 of 1	Archive leaderboard	report
Dependency Parsing	Penn Treebank	MFVI	LAS	95.34	#6 of 22	Archive leaderboard	report
Dependency Parsing	Penn Treebank	MFVI	UAS	96.91	#6 of 22	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

Adam Attention Attention Dropout BERT Dense Connections Dropout Layer Normalization Linear Layer Linear Warmup With Linear Decay Multi-Head Attention Residual Connection Softmax Weight Decay WordPiece

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