mlsanityData to 7 Oct 2026

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

arXiv 2108.07556 ↗First posted 17 Aug 2021cs.CLcited by 7

Not on the map. Why?

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.

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

Builds on

29 of 72 references.

References · 29

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
  3. 2019How multilingual is Multilingual BERT?cited by 642
  4. 2019On the Cross-lingual Transferability of Monolingual Representationscited by 575
  5. 2019Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERTcited by 301
  6. 2017Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Taggingcited by 71
  7. 2018Linguistically-Informed Self-Attention for Semantic Role Labelingcited by 71
  8. 2018Stack-Pointer Networks for Dependency Parsingcited by 36
  9. 2019Viable Dependency Parsing as Sequence Labelingcited by 34
  10. 2018NCRF++: An Open-source Neural Sequence Labeling Toolkitcited by 29
  11. 2016Many Languages, One Parsercited by 26
  12. 2019Deep Contextualized Self-training for Low Resource Dependency Parsingcited by 24
17 more
  1. 2019Left-to-Right Dependency Parsing with Pointer Networkscited by 21
  2. 2018Scheduled Multi-Task Learning: From Syntax to Translationcited by 18
  3. 2020On the Role of Supervision in Unsupervised Constituency Parsingcited by 18
  4. 2020Bracketing Encodings for 2-Planar Dependency Parsingcited by 15
  5. 2020A Unifying Theory of Transition-based and Sequence Labeling Parsingcited by 12
  6. 2019How to best use Syntax in Semantic Role Labellingcited by 11
  7. 2019Cross-Lingual Dependency Parsing Using Code-Mixed TreeBankcited by 10
  8. 2019Leveraging Dependency Forest for Neural Medical Relation Extractioncited by 10
  9. 2020Is POS Tagging Necessary or Even Helpful for Neural Dependency Parsing?cited by 9
  10. 2020Efficient EUD Parsingcited by 8
  11. 2019Low-Resource Parsing with Crosslingual Contextualized Representationscited by 5
  12. 2020Distilling Neural Networks for Greener and Faster Dependency Parsingcited by 5
  13. 2017Generic Axiomatization of Families of Noncrossing Graphs in Dependency Parsingcited by 4
  14. 2015Unsupervised Dependency Parsing: Let's Use Supervised Parserscited by 3
  15. 2017How Important is Syntactic Parsing Accuracy? An Empirical Evaluation on Rule-Based Sentiment Analysiscited by 3
  16. 2020Self-Training for Unsupervised Parsing with PRPNcited by 3
  17. 2021What Taggers Fail to Learn, Parsers Need the Mostcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 2; 2024: 1; 2025: 1.

7 papers.

  1. 20234 and 7-bit Labeling for Projective and Non-Projective Dependency Treescited by 8
  2. 2023Assessment of Pre-Trained Models Across Languages and Grammarscited by 2
  3. 2024Dependency Graph Parsing as Sequence Labelingcited by 2
  4. 2022Parsing linearizations appreciate PoS tags - but some are fussy about errorscited by 1
  5. 2025Hierarchical Bracketing Encodings for Dependency Parsing as Taggingcited by 1
  6. 2022Cross-lingual Inflection as a Data Augmentation Method for Parsingcited by 0
  7. 2022The Fragility of Multi-Treebank Parsing Evaluationcited by 0