# Discontinuous Constituent Parsing with Pointer Networks

arXiv: https://arxiv.org/abs/2002.01824 · HTML: https://mlsanity.com/paper/2002.01824/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Feb 2020.

## Built on by (most cited first, 6 of 6)

- [Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks](https://mlsanity.com/paper/2110.05419/) (2021)
- [Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive Grammars](https://mlsanity.com/paper/2212.09140/) (2022)
- [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)
- [Tree-Averaging Algorithms for Ensemble-Based Unsupervised Discontinuous Constituency Parsing](https://mlsanity.com/paper/2403.00143/) (2024)
- [Exploiting Pre-trained Encoder-Decoder Transformers for Sequence-to-Sequence Constituent Parsing](https://mlsanity.com/paper/2605.13373/) (2026)

## Abstract (arXiv)

One of the most complex syntactic representations used in computational linguistics and NLP are discontinuous constituent trees, crucial for representing all grammatical phenomena of languages such as German. Recent advances in dependency parsing have shown that Pointer Networks excel in efficiently parsing syntactic relations between words in a sentence. This kind of sequence-to-sequence models achieve outstanding accuracies in building non-projective dependency trees, but its potential has not been proved yet on a more difficult task. We propose a novel neural network architecture that, by means of Pointer Networks, is able to generate the most accurate discontinuous constituent representations to date, even without the need of Part-of-Speech tagging information. To do so, we internally model discontinuous constituent structures as augmented non-projective dependency structures. The proposed approach achieves state-of-the-art results on the two widely-used NEGRA and TIGER benchmarks, outperforming previous work by a wide margin.