# Deep Multitask Learning for Semantic Dependency Parsing

arXiv: https://arxiv.org/abs/1704.06855 · HTML: https://mlsanity.com/paper/1704.06855/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2017.

## Built on by (most cited first, 10 of 10)

- [Multi-Task Learning in Natural Language Processing: An Overview](https://mlsanity.com/paper/2109.09138/) (2021)
- [PVG at WASSA 2021: A Multi-Input, Multi-Task, Transformer-Based Architecture for Empathy and Distress Prediction](https://mlsanity.com/paper/2103.03296/) (2021)
- [Modeling Label Correlations for Second-Order Semantic Dependency Parsing with Mean-Field Inference](https://mlsanity.com/paper/2204.03619/) (2022)
- [Hierarchical Multitask Learning with Dependency Parsing for Japanese Semantic Role Labeling Improves Performance of Argument Identification](https://mlsanity.com/paper/2101.06071/) (2021)
- [Self-Attentive Constituency Parsing for UCCA-based Semantic Parsing](https://mlsanity.com/paper/2110.00621/) (2021)
- [A Higher-Order Semantic Dependency Parser](https://mlsanity.com/paper/2201.11312/) (2022)
- [Schema-Free Dependency Parsing via Sequence Generation](https://mlsanity.com/paper/2201.12407/) (2022)
- [Dependency Parsing is More Parameter-Efficient with Normalization](https://mlsanity.com/paper/2505.20215/) (2025)
- [Task Decomposition for Efficient Annotation](https://mlsanity.com/paper/2606.24734/) (2026)
- [Mapping the Concept Landscape: Structural Perception of Global Distributions for Transparent Data Pruning](https://mlsanity.com/paper/2608.22858/) (2026)

## Abstract (arXiv)

We present a deep neural architecture that parses sentences into three semantic dependency graph formalisms. By using efficient, nearly arc-factored inference and a bidirectional-LSTM composed with a multi-layer perceptron, our base system is able to significantly improve the state of the art for semantic dependency parsing, without using hand-engineered features or syntax. We then explore two multitask learning approaches---one that shares parameters across formalisms, and one that uses higher-order structures to predict the graphs jointly. We find that both approaches improve performance across formalisms on average, achieving a new state of the art. Our code is open-source and available at https://github.com/Noahs-ARK/NeurboParser.