# Multitask Pointer Network for Multi-Representational Parsing

arXiv: https://arxiv.org/abs/2009.09730 · HTML: https://mlsanity.com/paper/2009.09730/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2020.

## Built on by (most cited first, 12 of 12)

- [Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks](https://mlsanity.com/paper/2110.05419/) (2021)
- [Nested Named Entity Recognition as Latent Lexicalized Constituency Parsing](https://mlsanity.com/paper/2203.04665/) (2022)
- [Dependency Parsing as MRC-based Span-Span Prediction](https://mlsanity.com/paper/2105.07654/) (2021)
- [Headed-Span-Based Projective Dependency Parsing](https://mlsanity.com/paper/2108.04750/) (2021)
- [Reducing Discontinuous to Continuous Parsing with Pointer Network Reordering](https://mlsanity.com/paper/2104.06239/) (2021)
- [Dependency Parsing with Bottom-up Hierarchical Pointer Networks](https://mlsanity.com/paper/2105.09611/) (2021)
- [Discontinuous Grammar as a Foreign Language](https://mlsanity.com/paper/2110.10431/) (2021)
- [Transition-based Semantic Role Labeling with Pointer Networks](https://mlsanity.com/paper/2205.10023/) (2022)
- [Structured Sentiment Analysis as Transition-based Dependency Graph Parsing](https://mlsanity.com/paper/2305.05311/) (2023)
- [High-order Joint Constituency and Dependency Parsing](https://mlsanity.com/paper/2309.11888/) (2023)
- [Exploiting Pre-trained Encoder-Decoder Transformers for Sequence-to-Sequence Constituent Parsing](https://mlsanity.com/paper/2605.13373/) (2026)
- [Multi-Task Learning by using Contextualized Word Representations for Syntactic Parsing of a Morphologically Rich Language](https://mlsanity.com/paper/2609.29855/) (2026)

## Abstract (arXiv)

We propose a transition-based approach that, by training a single model, can efficiently parse any input sentence with both constituent and dependency trees, supporting both continuous/projective and discontinuous/non-projective syntactic structures. To that end, we develop a Pointer Network architecture with two separate task-specific decoders and a common encoder, and follow a multitask learning strategy to jointly train them. The resulting quadratic system, not only becomes the first parser that can jointly produce both unrestricted constituent and dependency trees from a single model, but also proves that both syntactic formalisms can benefit from each other during training, achieving state-of-the-art accuracies in several widely-used benchmarks such as the continuous English and Chinese Penn Treebanks, as well as the discontinuous German NEGRA and TIGER datasets.