Papers › Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal...

Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal Dynamic Oracles

20 Dec 2016EMNLP 2016 11arXiv:1612.06475archive 2025-07-28

James Cross, Liang Huang

Parsing accuracy using efficient greedy transition systems has improved dramatically in recent years thanks to neural networks. Despite striking results in dependency parsing, however, neural models have not surpassed state-of-the-art approaches in constituency parsing. To remedy this, we introduce a new shift-reduce system whose stack contains merely sentence spans, represented by a bare minimum of LSTM features. We also design the first provably optimal dynamic oracle for constituency parsing, which runs in amortized O(1) time, compared to O(n^3) oracles for standard dependency parsing. Training with this oracle, we achieve the best F1 scores on both English and French of any parser that does not use reranking or external data.

PaperPDFConference PDFCode

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

Code

jhcross/span-parser officialmentioned in paperMIT 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

Constituency ParsingDependency ParsingRerankingSentence

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

LSTMSigmoid ActivationTanh Activation

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