# Better, Faster, Stronger Sequence Tagging Constituent Parsers

arXiv: https://arxiv.org/abs/1902.10985 · HTML: https://mlsanity.com/paper/1902.10985/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2019.

## Built on by (most cited first, 5 of 5)

- [Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks](https://mlsanity.com/paper/2110.05419/) (2021)
- [Structure-Unified M-Tree Coding Solver for MathWord Problem](https://mlsanity.com/paper/2210.12432/) (2022)
- [Order-sensitive Neural Constituency Parsing](https://mlsanity.com/paper/2211.00421/) (2022)
- [On Parsing as Tagging](https://mlsanity.com/paper/2211.07344/) (2022)
- [Nested Named Entity Recognition as Single-Pass Sequence Labeling](https://mlsanity.com/paper/2505.16855/) (2025)

## Abstract (arXiv)

Sequence tagging models for constituent parsing are faster, but less accurate than other types of parsers. In this work, we address the following weaknesses of such constituent parsers: (a) high error rates around closing brackets of long constituents, (b) large label sets, leading to sparsity, and (c) error propagation arising from greedy decoding. To effectively close brackets, we train a model that learns to switch between tagging schemes. To reduce sparsity, we decompose the label set and use multi-task learning to jointly learn to predict sublabels. Finally, we mitigate issues from greedy decoding through auxiliary losses and sentence-level fine-tuning with policy gradient. Combining these techniques, we clearly surpass the performance of sequence tagging constituent parsers on the English and Chinese Penn Treebanks, and reduce their parsing time even further. On the SPMRL datasets, we observe even greater improvements across the board, including a new state of the art on Basque, Hebrew, Polish and Swedish.