# Is POS Tagging Necessary or Even Helpful for Neural Dependency Parsing?

arXiv: https://arxiv.org/abs/2003.03204 · HTML: https://mlsanity.com/paper/2003.03204/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Mar 2020.

## Built on by (most cited first, 9 of 9)

- [Specializing Multilingual Language Models: An Empirical Study](https://mlsanity.com/paper/2106.09063/) (2021)
- [A Modest Pareto Optimisation Analysis of Dependency Parsers in 2021](https://mlsanity.com/paper/2106.04216/) (2021)
- [Not All Linearizations Are Equally Data-Hungry in Sequence Labeling Parsing](https://mlsanity.com/paper/2108.07556/) (2021)
- [A Falta de Pan, Buenas Son Tortas: The Efficacy of Predicted UPOS Tags for Low Resource UD Parsing](https://mlsanity.com/paper/2106.04222/) (2021)
- [What Taggers Fail to Learn, Parsers Need the Most](https://mlsanity.com/paper/2104.01083/) (2021)
- [Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging](https://mlsanity.com/paper/2203.10315/) (2022)
- [Parsing linearizations appreciate PoS tags - but some are fussy about errors](https://mlsanity.com/paper/2210.15219/) (2022)
- [Another Dead End for Morphological Tags? Perturbed Inputs and Parsing](https://mlsanity.com/paper/2305.15119/) (2023)
- [Building Foundations for Natural Language Processing of Historical Turkish: Resources and Models](https://mlsanity.com/paper/2501.04828/) (2025)

## Abstract (arXiv)

In the pre deep learning era, part-of-speech tags have been considered as indispensable ingredients for feature engineering in dependency parsing. But quite a few works focus on joint tagging and parsing models to avoid error propagation. In contrast, recent studies suggest that POS tagging becomes much less important or even useless for neural parsing, especially when using character-based word representations. Yet there are not enough investigations focusing on this issue, both empirically and linguistically. To answer this, we design and compare three typical multi-task learning framework, i.e., Share-Loose, Share-Tight, and Stack, for joint tagging and parsing based on the state-of-the-art biaffine parser. Considering that it is much cheaper to annotate POS tags than parse trees, we also investigate the utilization of large-scale heterogeneous POS tag data. We conduct experiments on both English and Chinese datasets, and the results clearly show that POS tagging (both homogeneous and heterogeneous) can still significantly improve parsing performance when using the Stack joint framework. We conduct detailed analysis and gain more insights from the linguistic aspect.