# Multitask Parsing Across Semantic Representations

arXiv: https://arxiv.org/abs/1805.00287 · HTML: https://mlsanity.com/paper/1805.00287/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2018.

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

- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Multi-Task Learning in Natural Language Processing: An Overview](https://mlsanity.com/paper/2109.09138/) (2021)
- [Specializing Multilingual Language Models: An Empirical Study](https://mlsanity.com/paper/2106.09063/) (2021)
- [Pay More Attention to Relation Exploration for Knowledge Base Question Answering](https://mlsanity.com/paper/2305.02118/) (2023)
- [On the Relation between Syntactic Divergence and Zero-Shot Performance](https://mlsanity.com/paper/2110.04644/) (2021)
- [One Semantic Parser to Parse Them All: Sequence to Sequence Multi-Task Learning on Semantic Parsing Datasets](https://mlsanity.com/paper/2106.04476/) (2021)
- [Cross-domain Generalization for AMR Parsing](https://mlsanity.com/paper/2210.12445/) (2022)
- [Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm](https://mlsanity.com/paper/2307.13424/) (2023)
- [Enhancing the Transformer Decoder with Transition-based Syntax](https://mlsanity.com/paper/2101.12640/) (2021)
- [Self-Attentive Constituency Parsing for UCCA-based Semantic Parsing](https://mlsanity.com/paper/2110.00621/) (2021)

## Abstract (arXiv)

The ability to consolidate information of different types is at the core of intelligence, and has tremendous practical value in allowing learning for one task to benefit from generalizations learned for others. In this paper we tackle the challenging task of improving semantic parsing performance, taking UCCA parsing as a test case, and AMR, SDP and Universal Dependencies (UD) parsing as auxiliary tasks. We experiment on three languages, using a uniform transition-based system and learning architecture for all parsing tasks. Despite notable conceptual, formal and domain differences, we show that multitask learning significantly improves UCCA parsing in both in-domain and out-of-domain settings.