# Neural Transition-based Syntactic Linearization

arXiv: https://arxiv.org/abs/1810.09609 · HTML: https://mlsanity.com/paper/1810.09609/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2018.

## Built on by (most cited first, 3 of 3)

- [Studying word order through iterative shuffling](https://mlsanity.com/paper/2109.04867/) (2021)
- [On the Role of Pre-trained Language Models in Word Ordering: A Case Study with BART](https://mlsanity.com/paper/2204.07367/) (2022)
- [A tree interpretation of arc standard dependency derivation](https://mlsanity.com/paper/2603.27459/) (2026)

## Abstract (arXiv)

The task of linearization is to find a grammatical order given a set of words. Traditional models use statistical methods. Syntactic linearization systems, which generate a sentence along with its syntactic tree, have shown state-of-the-art performance. Recent work shows that a multi-layer LSTM language model outperforms competitive statistical syntactic linearization systems without using syntax. In this paper, we study neural syntactic linearization, building a transition-based syntactic linearizer leveraging a feed-forward neural network, observing significantly better results compared to LSTM language models on this task.