# Not All Linearizations Are Equally Data-Hungry in Sequence Labeling Parsing

arXiv: https://arxiv.org/abs/2108.07556 · HTML: https://mlsanity.com/paper/2108.07556/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 72 references that are in the map.
- First posted on arXiv 17 Aug 2021.

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [On the Cross-lingual Transferability of Monolingual Representations](https://mlsanity.com/paper/1910.11856/) (2019)
- [Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT](https://mlsanity.com/paper/1904.09077/) (2019)
- [Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging](https://mlsanity.com/paper/1707.09861/) (2017)
- [Linguistically-Informed Self-Attention for Semantic Role Labeling](https://mlsanity.com/paper/1804.08199/) (2018)
- [Stack-Pointer Networks for Dependency Parsing](https://mlsanity.com/paper/1805.01087/) (2018)
- [Viable Dependency Parsing as Sequence Labeling](https://mlsanity.com/paper/1902.10505/) (2019)
- [NCRF++: An Open-source Neural Sequence Labeling Toolkit](https://mlsanity.com/paper/1806.05626/) (2018)
- [Many Languages, One Parser](https://mlsanity.com/paper/1602.01595/) (2016)
- [Deep Contextualized Self-training for Low Resource Dependency Parsing](https://mlsanity.com/paper/1911.04286/) (2019)
- [Left-to-Right Dependency Parsing with Pointer Networks](https://mlsanity.com/paper/1903.08445/) (2019)
- [Scheduled Multi-Task Learning: From Syntax to Translation](https://mlsanity.com/paper/1804.08915/) (2018)
- [On the Role of Supervision in Unsupervised Constituency Parsing](https://mlsanity.com/paper/2010.02423/) (2020)
- [Bracketing Encodings for 2-Planar Dependency Parsing](https://mlsanity.com/paper/2011.00596/) (2020)
- [A Unifying Theory of Transition-based and Sequence Labeling Parsing](https://mlsanity.com/paper/2011.00584/) (2020)
- [How to best use Syntax in Semantic Role Labelling](https://mlsanity.com/paper/1906.00266/) (2019)
- [Cross-Lingual Dependency Parsing Using Code-Mixed TreeBank](https://mlsanity.com/paper/1909.02235/) (2019)
- [Leveraging Dependency Forest for Neural Medical Relation Extraction](https://mlsanity.com/paper/1911.04123/) (2019)
- [Is POS Tagging Necessary or Even Helpful for Neural Dependency Parsing?](https://mlsanity.com/paper/2003.03204/) (2020)
- [Efficient EUD Parsing](https://mlsanity.com/paper/2006.00838/) (2020)
- [Low-Resource Parsing with Crosslingual Contextualized Representations](https://mlsanity.com/paper/1909.08744/) (2019)
- [Distilling Neural Networks for Greener and Faster Dependency Parsing](https://mlsanity.com/paper/2006.00844/) (2020)
- [Generic Axiomatization of Families of Noncrossing Graphs in Dependency Parsing](https://mlsanity.com/paper/1706.03357/) (2017)
- [Unsupervised Dependency Parsing: Let's Use Supervised Parsers](https://mlsanity.com/paper/1504.04666/) (2015)
- [How Important is Syntactic Parsing Accuracy? An Empirical Evaluation on Rule-Based Sentiment Analysis](https://mlsanity.com/paper/1706.02141/) (2017)
- [Self-Training for Unsupervised Parsing with PRPN](https://mlsanity.com/paper/2005.13455/) (2020)
- [What Taggers Fail to Learn, Parsers Need the Most](https://mlsanity.com/paper/2104.01083/) (2021)

## Built on by (most cited first, 7 of 7)

- [4 and 7-bit Labeling for Projective and Non-Projective Dependency Trees](https://mlsanity.com/paper/2310.14319/) (2023)
- [Assessment of Pre-Trained Models Across Languages and Grammars](https://mlsanity.com/paper/2309.11165/) (2023)
- [Dependency Graph Parsing as Sequence Labeling](https://mlsanity.com/paper/2410.17972/) (2024)
- [Parsing linearizations appreciate PoS tags - but some are fussy about errors](https://mlsanity.com/paper/2210.15219/) (2022)
- [Hierarchical Bracketing Encodings for Dependency Parsing as Tagging](https://mlsanity.com/paper/2505.11693/) (2025)
- [Cross-lingual Inflection as a Data Augmentation Method for Parsing](https://mlsanity.com/paper/2205.09350/) (2022)
- [The Fragility of Multi-Treebank Parsing Evaluation](https://mlsanity.com/paper/2209.06699/) (2022)

## Abstract (arXiv)

Different linearizations have been proposed to cast dependency parsing as sequence labeling and solve the task as: (i) a head selection problem, (ii) finding a representation of the token arcs as bracket strings, or (iii) associating partial transition sequences of a transition-based parser to words. Yet, there is little understanding about how these linearizations behave in low-resource setups. Here, we first study their data efficiency, simulating data-restricted setups from a diverse set of rich-resource treebanks. Second, we test whether such differences manifest in truly low-resource setups. The results show that head selection encodings are more data-efficient and perform better in an ideal (gold) framework, but that such advantage greatly vanishes in favour of bracketing formats when the running setup resembles a real-world low-resource configuration.