# Shift-Reduce Constituent Parsing with Neural Lookahead Features

arXiv: https://arxiv.org/abs/1612.00567 · HTML: https://mlsanity.com/paper/1612.00567/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Dec 2016.

## Built on by (most cited first, 8 of 8)

- [A Conditional Splitting Framework for Efficient Constituency Parsing](https://mlsanity.com/paper/2106.15760/) (2021)
- [In-Order Chart-Based Constituent Parsing](https://mlsanity.com/paper/2102.04065/) (2021)
- [Neural Combinatory Constituency Parsing](https://mlsanity.com/paper/2106.06689/) (2021)
- [Fast Rule-Based Decoding: Revisiting Syntactic Rules in Neural Constituency Parsing](https://mlsanity.com/paper/2212.08458/) (2022)
- [jp-evalb: Robust Alignment-based PARSEVAL Measures](https://mlsanity.com/paper/2405.14150/) (2024)
- [Order-sensitive Neural Constituency Parsing](https://mlsanity.com/paper/2211.00421/) (2022)
- [Cross-domain Chinese Sentence Pattern Parsing](https://mlsanity.com/paper/2402.16311/) (2024)
- [Non-binary bottom-up constituency parsing without arity actions](https://mlsanity.com/paper/2607.10591/) (2026)

## Abstract (arXiv)

Transition-based models can be fast and accurate for constituent parsing. Compared with chart-based models, they leverage richer features by extracting history information from a parser stack, which spans over non-local constituents. On the other hand, during incremental parsing, constituent information on the right hand side of the current word is not utilized, which is a relative weakness of shift-reduce parsing. To address this limitation, we leverage a fast neural model to extract lookahead features. In particular, we build a bidirectional LSTM model, which leverages the full sentence information to predict the hierarchy of constituents that each word starts and ends. The results are then passed to a strong transition-based constituent parser as lookahead features. The resulting parser gives 1.3% absolute improvement in WSJ and 2.3% in CTB compared to the baseline, given the highest reported accuracies for fully-supervised parsing.