mlsanityData to 14 Oct 2026

Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Tagging

arXiv 2210.09840 ↗First posted 18 Oct 2022cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Part-of-Speech (POS) tagging is an important component of the NLP pipeline, but many low-resource languages lack labeled data for training. An established method for training a POS tagger in such a scenario is to create a labeled training set by transferring from high-resource languages. In this paper, we propose a novel method for transferring labels from multiple high-resource source to low-resource target languages. We formalize POS tag projection as graph-based label propagation. Given translations of a sentence in multiple languages, we create a graph with words as nodes and alignment links as edges by aligning words for all language pairs. We then propagate node labels from source to target using a Graph Neural Network augmented with transformer layers. We show that our propagation creates training sets that allow us to train POS taggers for a diverse set of languages. When combined with enhanced contextualized embeddings, our method achieves a new state-of-the-art for unsupervised POS tagging of low-resource languages.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 28 of its 68 references that are in the map. First posted on arXiv 18 Oct 2022.

Builds on

28 of 68 references.

References · 28

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2017Graph Attention Networkscited by 8,923
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  4. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 798
  5. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 754
  6. 2020Stanza: A Python Natural Language Processing Toolkit for Many Human Languagescited by 723
  7. 2019Choosing Transfer Languages for Cross-Lingual Learningcited by 144
  8. 2017Encoding Sentences with Graph Convolutional Networks for Semantic Role Labelingcited by 137
  9. 2020Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Predictioncited by 132
  10. 201975 Languages, 1 Model: Parsing Universal Dependencies Universallycited by 90
  11. 2017Graph Convolutional Encoders for Syntax-aware Neural Machine Translationcited by 70
  12. 2018Graph-to-Sequence Learning using Gated Graph Neural Networkscited by 61
16 more
  1. 2021How to Adapt Your Pretrained Multilingual Model to 1600 Languagescited by 54
  2. 2020Explicit Alignment Objectives for Multilingual Bidirectional Encoderscited by 50
  3. 2021Revisiting the Primacy of English in Zero-shot Cross-lingual Transfercited by 47
  4. 2022Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptationcited by 44
  5. 2019Small and Practical BERT Models for Sequence Labelingcited by 40
  6. 2018Sentence-State LSTM for Text Representationcited by 22
  7. 2019On Node Features for Graph Neural Networkscited by 21
  8. 2017Cross-lingual, Character-Level Neural Morphological Taggingcited by 17
  9. 2013Axioms for Centralitycited by 16
  10. 2016Cross-Lingual Morphological Tagging for Low-Resource Languagescited by 9
  11. 2016Learning when to trust distant supervision: An application to low-resource POS tagging using cross-lingual projectioncited by 8
  12. 2018Distant Supervision from Disparate Sources for Low-Resource Part-of-Speech Taggingcited by 8
  13. 2022Towards a Broad Coverage Named Entity Resource: A Data-Efficient Approach for Many Diverse Languagescited by 8
  14. 2016A Strong Baseline for Learning Cross-Lingual Word Embeddings from Sentence Alignmentscited by 6
  15. 2022Graph Neural Networks for Multiparallel Word Alignmentcited by 4
  16. 2021ParCourE: A Parallel Corpus Explorer for a Massively Multilingual Corpuscited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 0; 2025: 3.

4 papers.

  1. 2023Glot500: Scaling Multilingual Corpora and Language Models to 500 Languagescited by 116
  2. 2025The taggedPBC: Annotating a massive parallel corpus for crosslinguistic investigationscited by 2
  3. 2025Unveiling Factors for Enhanced POS Tagging: A Study of Low-Resource Medieval Romance Languagescited by 1
  4. 2025Extending dependencies to the taggedPBC: Word order in transitive clausescited by 0