# Strongly Incremental Constituency Parsing with Graph Neural Networks

arXiv: https://arxiv.org/abs/2010.14568 · HTML: https://mlsanity.com/paper/2010.14568/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Oct 2020.

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

- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks](https://mlsanity.com/paper/2110.05419/) (2021)
- [Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language Modeling](https://mlsanity.com/paper/2112.07874/) (2021)
- [A Double-Graph Based Framework for Frame Semantic Parsing](https://mlsanity.com/paper/2206.09158/) (2022)
- [Explainable Natural Language Processing for Corporate Sustainability Analysis](https://mlsanity.com/paper/2407.17487/) (2024)
- [Reducing Discontinuous to Continuous Parsing with Pointer Network Reordering](https://mlsanity.com/paper/2104.06239/) (2021)
- [Discontinuous Grammar as a Foreign Language](https://mlsanity.com/paper/2110.10431/) (2021)
- [Efficient Encoders for Streaming Sequence Tagging](https://mlsanity.com/paper/2301.09244/) (2023)
- [On the Challenges of Fully Incremental Neural Dependency Parsing](https://mlsanity.com/paper/2309.16254/) (2023)
- [Constituency Parsing using LLMs](https://mlsanity.com/paper/2310.19462/) (2023)
- [To be Continuous, or to be Discrete, Those are Bits of Questions](https://mlsanity.com/paper/2406.07812/) (2024)
- [An Attempt to Develop a Neural Parser based on Simplified Head-Driven Phrase Structure Grammar on Vietnamese](https://mlsanity.com/paper/2411.17270/) (2024)
- [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)
- [Structured Sentiment Analysis as Transition-based Dependency Graph Parsing](https://mlsanity.com/paper/2305.05311/) (2023)
- [From Partial to Strictly Incremental Constituent Parsing](https://mlsanity.com/paper/2402.02782/) (2024)
- [Graph Neural Networks for Natural Language Processing: A Survey](https://mlsanity.com/paper/2106.06090/) (2021)
- [Analyzing Vietnamese Legal Questions Using Deep Neural Networks with Biaffine Classifiers](https://mlsanity.com/paper/2304.14447/) (2023)
- [Strahler Number of Natural Language Sentences in Comparison with Random Trees](https://mlsanity.com/paper/2307.02697/) (2023)
- [Entity-Aware Biaffine Attention Model for Improved Constituent Parsing with Reduced Entity Violations](https://mlsanity.com/paper/2409.00625/) (2024)
- [Train Once for All: A Transitional Approach for Efficient Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2412.00208/) (2024)
- [Exploiting Pre-trained Encoder-Decoder Transformers for Sequence-to-Sequence Constituent Parsing](https://mlsanity.com/paper/2605.13373/) (2026)

## Abstract (arXiv)

Parsing sentences into syntax trees can benefit downstream applications in NLP. Transition-based parsers build trees by executing actions in a state transition system. They are computationally efficient, and can leverage machine learning to predict actions based on partial trees. However, existing transition-based parsers are predominantly based on the shift-reduce transition system, which does not align with how humans are known to parse sentences. Psycholinguistic research suggests that human parsing is strongly incremental: humans grow a single parse tree by adding exactly one token at each step. In this paper, we propose a novel transition system called attach-juxtapose. It is strongly incremental; it represents a partial sentence using a single tree; each action adds exactly one token into the partial tree. Based on our transition system, we develop a strongly incremental parser. At each step, it encodes the partial tree using a graph neural network and predicts an action. We evaluate our parser on Penn Treebank (PTB) and Chinese Treebank (CTB). On PTB, it outperforms existing parsers trained with only constituency trees; and it performs on par with state-of-the-art parsers that use dependency trees as additional training data. On CTB, our parser establishes a new state of the art. Code is available at https://github.com/princeton-vl/attach-juxtapose-parser.