# Better, Faster, Stronger Sequence Tagging Constituent Parsers

## TL;DR

This paper introduces novel techniques to improve sequence tagging constituent parsers, making them more accurate and faster, and achieves state-of-the-art results across multiple languages and datasets.

## Contribution

The paper presents a combination of training strategies, label decomposition, and auxiliary losses to enhance sequence tagging parsers for constituent parsing.

## Key findings

- Surpassed previous sequence tagging parsers on English and Chinese Penn Treebanks.
- Achieved state-of-the-art results on Basque, Hebrew, Polish, and Swedish datasets.
- Reduced parsing time while improving accuracy.

## Abstract

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.