# Sequence Labeling Parsing by Learning Across Representations

arXiv: https://arxiv.org/abs/1907.01339 · HTML: https://mlsanity.com/paper/1907.01339/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2019.

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

- [FCDS: Fusing Constituency and Dependency Syntax into Document-Level Relation Extraction](https://mlsanity.com/paper/2403.01886/) (2024)
- [Structure-Unified M-Tree Coding Solver for MathWord Problem](https://mlsanity.com/paper/2210.12432/) (2022)
- [Syntactic Multi-view Learning for Open Information Extraction](https://mlsanity.com/paper/2212.02068/) (2022)
- [A Syntax-Injected Approach for Faster and More Accurate Sentiment Analysis](https://mlsanity.com/paper/2406.15163/) (2024)
- [Dancing in the syntax forest: fast, accurate and explainable sentiment analysis with SALSA](https://mlsanity.com/paper/2406.16071/) (2024)
- [Splitting EUD graphs into trees: A quick and clatty approach](https://mlsanity.com/paper/2106.13155/) (2021)
- [Learning Semantic Role Labeling from Compatible Label Sequences](https://mlsanity.com/paper/2305.14600/) (2023)
- [High-order Joint Constituency and Dependency Parsing](https://mlsanity.com/paper/2309.11888/) (2023)
- [Entity-Aware Biaffine Attention Model for Improved Constituent Parsing with Reduced Entity Violations](https://mlsanity.com/paper/2409.00625/) (2024)
- [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 use parsing as sequence labeling as a common framework to learn across constituency and dependency syntactic abstractions. To do so, we cast the problem as multitask learning (MTL). First, we show that adding a parsing paradigm as an auxiliary loss consistently improves the performance on the other paradigm. Secondly, we explore an MTL sequence labeling model that parses both representations, at almost no cost in terms of performance and speed. The results across the board show that on average MTL models with auxiliary losses for constituency parsing outperform single-task ones by 1.14 F1 points, and for dependency parsing by 0.62 UAS points.