# Parsing All: Syntax and Semantics, Dependencies and Spans

arXiv: https://arxiv.org/abs/1908.11522 · HTML: https://mlsanity.com/paper/1908.11522/

## Key facts

- Cited by 13 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 30 Aug 2019.

## Built on by (most cited first, 13 of 13)

- [Structural Pre-training for Dialogue Comprehension](https://mlsanity.com/paper/2105.10956/) (2021)
- [Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments](https://mlsanity.com/paper/2110.06865/) (2021)
- [Syntax-Aware Graph-to-Graph Transformer for Semantic Role Labelling](https://mlsanity.com/paper/2104.07704/) (2021)
- [Hyperbolic Relevance Matching for Neural Keyphrase Extraction](https://mlsanity.com/paper/2205.02047/) (2022)
- [Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers](https://mlsanity.com/paper/2307.00631/) (2023)
- [Transformers as Graph-to-Graph Models](https://mlsanity.com/paper/2310.17936/) (2023)
- [An MRC Framework for Semantic Role Labeling](https://mlsanity.com/paper/2109.06660/) (2021)
- [Transition-based Semantic Role Labeling with Pointer Networks](https://mlsanity.com/paper/2205.10023/) (2022)
- [The Role of Syntactic Span Preferences in Post-Hoc Explanation Disagreement](https://mlsanity.com/paper/2403.19424/) (2024)
- [Splitting EUD graphs into trees: A quick and clatty approach](https://mlsanity.com/paper/2106.13155/) (2021)
- [Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing](https://mlsanity.com/paper/2112.02970/) (2021)
- [Neural Unsupervised Semantic Role Labeling](https://mlsanity.com/paper/2104.09047/) (2021)
- [Syntax vs. Semantics: How Transformers Learn Deep Dependencies](https://mlsanity.com/paper/2608.26139/) (2026)

## Abstract (arXiv)

Both syntactic and semantic structures are key linguistic contextual clues, in which parsing the latter has been well shown beneficial from parsing the former. However, few works ever made an attempt to let semantic parsing help syntactic parsing. As linguistic representation formalisms, both syntax and semantics may be represented in either span (constituent/phrase) or dependency, on both of which joint learning was also seldom explored. In this paper, we propose a novel joint model of syntactic and semantic parsing on both span and dependency representations, which incorporates syntactic information effectively in the encoder of neural network and benefits from two representation formalisms in a uniform way. The experiments show that semantics and syntax can benefit each other by optimizing joint objectives. Our single model achieves new state-of-the-art or competitive results on both span and dependency semantic parsing on Propbank benchmarks and both dependency and constituent syntactic parsing on Penn Treebank.