mlsanityData to 7 Oct 2026

Bootstrapping Multilingual AMR with Contextual Word Alignments

arXiv 2102.02189 ↗First posted 3 Feb 2021cs.CL cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

We develop high performance multilingualAbstract Meaning Representation (AMR) sys-tems by projecting English AMR annotationsto other languages with weak supervision. Weachieve this goal by bootstrapping transformer-based multilingual word embeddings, in partic-ular those from cross-lingual RoBERTa (XLM-R large). We develop a novel technique forforeign-text-to-English AMR alignment, usingthe contextual word alignment between En-glish and foreign language tokens. This wordalignment is weakly supervised and relies onthe contextualized XLM-R word embeddings.We achieve a highly competitive performancethat surpasses the best published results forGerman, Italian, Spanish and Chinese.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 20 of its 41 references that are in the map. First posted on arXiv 3 Feb 2021.

Builds on

20 of 41 references.

References · 20

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  4. 2017Word Translation Without Parallel Datacited by 480
  5. 2019Massively Multilingual Neural Machine Translationcited by 246
  6. 2013Exploiting Similarities among Languages for Machine Translationcited by 187
  7. 2018A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddingscited by 145
  8. 2017A Survey Of Cross-lingual Word Embedding Modelscited by 142
  9. 2020Multilingual Alignment of Contextual Word Representationscited by 113
  10. 2017Offline bilingual word vectors, orthogonal transformations and the inverted softmaxcited by 94
  11. 2019Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsingcited by 69
  12. 2017Neural AMR: Sequence-to-Sequence Models for Parsing and Generationcited by 56
8 more
  1. 2020GPT-too: A language-model-first approach for AMR-to-text generationcited by 38
  2. 2020Transition-based Parsing with Stack-Transformerscited by 37
  3. 2018AMR Parsing as Graph Prediction with Latent Alignmentcited by 36
  4. 2019Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learningcited by 25
  5. 2017Cross-lingual Abstract Meaning Representation Parsingcited by 19
  6. 2017Neural Semantic Parsing by Character-based Translation: Experiments with Abstract Meaning Representationscited by 18
  7. 2020Pushing the Limits of AMR Parsing with Self-Learningcited by 16
  8. 2017AMR Parsing using Stack-LSTMscited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 1; 2023: 0; 2024: 1; 2025: 0; 2026: 1.

8 papers.

  1. 2021Maximum Bayes Smatch Ensemble Distillation for AMR Parsingcited by 27
  2. 2021Translate, then Parse! A strong baseline for Cross-Lingual AMR Parsingcited by 15
  3. 2021Weisfeiler-Leman in the BAMBOO: Novel AMR Graph Metrics and a Benchmark for AMR Graph Similaritycited by 15
  4. 2021Multilingual AMR Parsing with Noisy Knowledge Distillationcited by 8
  5. 2022Retrofitting Multilingual Sentence Embeddings with Abstract Meaning Representationcited by 4
  6. 2021Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generationcited by 3
  7. 2024Should Cross-Lingual AMR Parsing go Meta? An Empirical Assessment of Meta-Learning and Joint Learning AMR Parsingcited by 2
  8. 2026Effective QA-driven Annotation of Predicate-Argument Relations Across Languagescited by 0