# In-Order Transition-based Constituent Parsing

arXiv: https://arxiv.org/abs/1707.05000 · HTML: https://mlsanity.com/paper/1707.05000/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2017.

## Built on by (most cited first, 23 of 23)

- [Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks](https://mlsanity.com/paper/2110.05419/) (2021)
- [BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing](https://mlsanity.com/paper/2206.10668/) (2022)
- [Investigating Non-local Features for Neural Constituency Parsing](https://mlsanity.com/paper/2109.12814/) (2021)
- [Discontinuous Grammar as a Foreign Language](https://mlsanity.com/paper/2110.10431/) (2021)
- [Hermes: Unlocking Security Analysis of Cellular Network Protocols by Synthesizing Finite State Machines from Natural Language Specifications](https://mlsanity.com/paper/2310.04381/) (2023)
- [LLM-enhanced Self-training for Cross-domain Constituency Parsing](https://mlsanity.com/paper/2311.02660/) (2023)
- [Generating CCG Categories](https://mlsanity.com/paper/2103.08139/) (2021)
- [Head-driven Phrase Structure Parsing in O(n3) Time Complexity](https://mlsanity.com/paper/2105.09835/) (2021)
- [Scene Graph Modification as Incremental Structure Expanding](https://mlsanity.com/paper/2209.09093/) (2022)
- [Constituency Parsing using LLMs](https://mlsanity.com/paper/2310.19462/) (2023)
- [In-Order Chart-Based Constituent Parsing](https://mlsanity.com/paper/2102.04065/) (2021)
- [Neural Combinatory Constituency Parsing](https://mlsanity.com/paper/2106.06689/) (2021)
- [Unleashing the True Potential of Sequence-to-Sequence Models for Sequence Tagging and Structure Parsing](https://mlsanity.com/paper/2302.02275/) (2023)
- [Shift-Reduce Task-Oriented Semantic Parsing with Stack-Transformers](https://mlsanity.com/paper/2210.11984/) (2022)
- [Joint Chinese Word Segmentation and Span-based Constituency Parsing](https://mlsanity.com/paper/2211.01638/) (2022)
- [On Parsing as Tagging](https://mlsanity.com/paper/2211.07344/) (2022)
- [Contrastive Learning on LLM Back Generation Treebank for Cross-domain Constituency Parsing](https://mlsanity.com/paper/2505.20976/) (2025)
- [Punctuation-aware treebank tree binarization](https://mlsanity.com/paper/2510.10951/) (2025)
- [A tree interpretation of arc standard dependency derivation](https://mlsanity.com/paper/2603.27459/) (2026)
- [Exploiting Pre-trained Encoder-Decoder Transformers for Sequence-to-Sequence Constituent Parsing](https://mlsanity.com/paper/2605.13373/) (2026)
- [Does Traversal Order Matter? A Systematic Study of Tree Traversal Methods in Transformer Grammars](https://mlsanity.com/paper/2606.16836/) (2026)
- [Non-binary bottom-up constituency parsing without arity actions](https://mlsanity.com/paper/2607.10591/) (2026)
- [Representing and Parsing Korean Constituency Structure at Different Levels of Granularity](https://mlsanity.com/paper/2608.27035/) (2026)

## Abstract (arXiv)

Both bottom-up and top-down strategies have been used for neural transition-based constituent parsing. The parsing strategies differ in terms of the order in which they recognize productions in the derivation tree, where bottom-up strategies and top-down strategies take post-order and pre-order traversal over trees, respectively. Bottom-up parsers benefit from rich features from readily built partial parses, but lack lookahead guidance in the parsing process; top-down parsers benefit from non-local guidance for local decisions, but rely on a strong encoder over the input to predict a constituent hierarchy before its construction.To mitigate both issues, we propose a novel parsing system based on in-order traversal over syntactic trees, designing a set of transition actions to find a compromise between bottom-up constituent information and top-down lookahead information. Based on stack-LSTM, our psycholinguistically motivated constituent parsing system achieves 91.8 F1 on WSJ benchmark. Furthermore, the system achieves 93.6 F1 with supervised reranking and 94.2 F1 with semi-supervised reranking, which are the best results on the WSJ benchmark.