mlsanityData to 7 Oct 2026

Zero-shot Dependency Parsing with Unsupervised Cross-Lingual Bootstrapping

arXiv 2609.37883 ↗First posted 29 Sep 2026cs.CLcited by 0

New in Synthetic data and self-improvement for LLMs; no direction yet. Synthetic data and self-improvement for LLMs

Abstract (arXiv)

Pre-trained language models (PLMs) with encoder-based architectures have shown impressive capabilities in zero-shot cross-lingual transfer for various language understanding tasks. However, applying this technique to dependency parsing remains a significant challenge due to its syntactic nature. To boost model generalizability across linguistic typologies, we propose a cross-lingual unsupervised bootstrapping method to improve syntactic knowledge within the PLM. We show that our method achieves a significant improvement in zero-shot parsing performance in low-resource languages. Analysis of these bootstrapped models uncovers increased robustness in recognizing syntactic structures, evidenced by higher scores in parameter-free tree probing tests.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 25 references that are in the map. First posted on arXiv 29 Sep 2026.

Builds on

19 of 25 references.

References · 19

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  4. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  5. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  6. 2019Similarity of Neural Network Representations Revisitedcited by 1,695
  7. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
  8. 2019Cross-lingual Language Model Pretrainingcited by 1,088
  9. 2019How multilingual is Multilingual BERT?cited by 642
  10. 2020Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERTcited by 109
  11. 201975 Languages, 1 Model: Parsing Universal Dependencies Universallycited by 90
  12. 2020UDapter: Language Adaptation for Truly Universal Dependency Parsingcited by 77
7 more
  1. 2017Learning Language Representations for Typology Predictioncited by 40
  2. 2022English Contrastive Learning Can Learn Universal Cross-lingual Sentence Embeddingscited by 26
  3. 2019Zero-shot Dependency Parsing with Pre-trained Multilingual Sentence Representationscited by 17
  4. 2022Don't Judge a Language Model by Its Last Layer: Contrastive Learning with Layer-Wise Attention Poolingcited by 12
  5. 2021Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsingcited by 10
  6. 2022Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learningcited by 5
  7. 2023Improving Cross-Lingual Transfer through Subtree-Aware Word Reorderingcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Bootstrapping Multilingual Semantic Parsers using Large Language Models
  2. 2025Step-by-step Instructions and a Simple Tabular Output Format Improve the Dependency Parsing Accuracy of LLMs
  3. 2023Translate to Disambiguate: Zero-shot Multilingual Word Sense Disambiguation with Pretrained Language Models
  4. 2022Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective
  5. 2021Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Data
  6. 2025CycleDistill: Bootstrapping Machine Translation using LLMs with Cyclical Distillation
  7. 2023Combating the Curse of Multilinguality in Cross-Lingual WSD by Aligning Sparse Contextualized Word Representations
  8. 2021XeroAlign: Zero-Shot Cross-lingual Transformer Alignment