mlsanityData to 7 Oct 2026

A Modest Pareto Optimisation Analysis of Dependency Parsers in 2021

arXiv 2106.04216 ↗First posted 8 Jun 2021cs.CL cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

We evaluate three leading dependency parser systems from different paradigms on a small yet diverse subset of languages in terms of their accuracy-efficiency Pareto front. As we are interested in efficiency, we evaluate core parsers without pretrained language models (as these are typically huge networks and would constitute most of the compute time) or other augmentations that can be transversally applied to any of them. Biaffine parsing emerges as a well-balanced default choice, with sequence-labelling parsing being preferable if inference speed (but not training energy cost) is the priority.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 21 of its 64 references that are in the map. First posted on arXiv 8 Jun 2021.

Builds on

21 of 64 references.

References · 21

  1. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
  2. 2016Deep Biaffine Attention for Neural Dependency Parsingcited by 334
  3. 2018Learning Word Vectors for 157 Languagescited by 279
  4. 2018Semi-Supervised Sequence Modeling with Cross-View Trainingcited by 75
  5. 2016Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representationscited by 55
  6. 2018Analogical Reasoning on Chinese Morphological and Semantic Relationscited by 50
  7. 2020Efficient Second-Order TreeCRF for Neural Dependency Parsingcited by 48
  8. 2019Head-Driven Phrase Structure Grammar Parsing on Penn Treebankcited by 43
  9. 2018Stack-Pointer Networks for Dependency Parsingcited by 36
  10. 2019Viable Dependency Parsing as Sequence Labelingcited by 34
  11. 2019Left-to-Right Dependency Parsing with Pointer Networkscited by 21
  12. 2020HULK: An Energy Efficiency Benchmark Platform for Responsible Natural Language Processingcited by 16
9 more
  1. 2020Bracketing Encodings for 2-Planar Dependency Parsingcited by 15
  2. 2016Distilling an Ensemble of Greedy Dependency Parsers into One MST Parsercited by 11
  3. 201882 Treebanks, 34 Models: Universal Dependency Parsing with Multi-Treebank Modelscited by 11
  4. 2018An Investigation of the Interactions Between Pre-Trained Word Embeddings, Character Models and POS Tags in Dependency Parsingcited by 10
  5. 2020Is POS Tagging Necessary or Even Helpful for Neural Dependency Parsing?cited by 9
  6. 2020Efficient EUD Parsingcited by 8
  7. 2020Distilling Neural Networks for Greener and Faster Dependency Parsingcited by 5
  8. 2020On the Frailty of Universal POS Tags for Neural UD Parserscited by 4
  9. 2021Optimal Size-Performance Tradeoffs: Weighing PoS Tagger Modelscited by 2

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 4; 2023: 2; 2024: 2.

9 papers.

  1. 2022Towards Climate Awareness in NLP Researchcited by 19
  2. 2022Stochastic Multiple Target Sampling Gradient Descentcited by 14
  3. 20234 and 7-bit Labeling for Projective and Non-Projective Dependency Treescited by 8
  4. 2023On the Challenges of Fully Incremental Neural Dependency Parsingcited by 2
  5. 2024A Syntax-Injected Approach for Faster and More Accurate Sentiment Analysiscited by 2
  6. 2024Dancing in the syntax forest: fast, accurate and explainable sentiment analysis with SALSAcited by 2
  7. 2021Splitting EUD graphs into trees: A quick and clatty approachcited by 1
  8. 2022Parsing linearizations appreciate PoS tags - but some are fussy about errorscited by 1
  9. 2022The Fragility of Multi-Treebank Parsing Evaluationcited by 0