mlsanityData to 7 Oct 2026

Multilingual AMR Parsing with Noisy Knowledge Distillation

arXiv 2109.15196 ↗First posted 30 Sep 2021cs.CL cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

We study multilingual AMR parsing from the perspective of knowledge distillation, where the aim is to learn and improve a multilingual AMR parser by using an existing English parser as its teacher. We constrain our exploration in a strict multilingual setting: there is but one model to parse all different languages including English. We identify that noisy input and precise output are the key to successful distillation. Together with extensive pre-training, we obtain an AMR parser whose performances surpass all previously published results on four different foreign languages, including German, Spanish, Italian, and Chinese, by large margins (up to 18.8 textscSmatch points on Chinese and on average 11.3 textscSmatch points). Our parser also achieves comparable performance on English to the latest state-of-the-art English-only parser.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 39 of its 57 references that are in the map. First posted on arXiv 30 Sep 2021.

Builds on

39 of 57 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  6. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  7. 2014FitNets: Hints for Thin Deep Netscited by 1,619
  8. 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,059
  9. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
  10. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  11. 2016Sequence-Level Knowledge Distillationcited by 761
  12. 2020XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalizationcited by 738
27 more
  1. 2013Do Deep Nets Really Need to be Deep?cited by 466
  2. 2017Non-Autoregressive Neural Machine Translationcited by 457
  3. 2018Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyondcited by 434
  4. 2020Multilingual Translation with Extensible Multilingual Pretraining and Finetuningcited by 287
  5. 2020XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generationcited by 221
  6. 2019Understanding Knowledge Distillation in Non-autoregressive Machine Translationcited by 121
  7. 2019Multilingual Neural Machine Translation with Knowledge Distillationcited by 95
  8. 2017Neural AMR: Sequence-to-Sequence Models for Parsing and Generationcited by 56
  9. 2019AMR Parsing as Sequence-to-Graph Transductioncited by 50
  10. 2020AMR Parsing via Graph-Sequence Iterative Inferencecited by 47
  11. 2017Ensemble Distillation for Neural Machine Translationcited by 39
  12. 2019Semantic Neural Machine Translation using AMRcited by 37
  13. 2018Abstract Meaning Representation for Multi-Document Summarizationcited by 35
  14. 2019Broad-Coverage Semantic Parsing as Transductioncited by 32
  15. 2020Noisy Self-Knowledge Distillation for Text Summarizationcited by 31
  16. 2020Improving AMR Parsing with Sequence-to-Sequence Pre-trainingcited by 30
  17. 2019Core Semantic First: A Top-down Approach for AMR Parsingcited by 24
  18. 2017Cross-lingual Abstract Meaning Representation Parsingcited by 19
  19. 2017Neural Semantic Parsing by Character-based Translation: Experiments with Abstract Meaning Representationscited by 18
  20. 2018Attention-Guided Answer Distillation for Machine Reading Comprehensioncited by 18
  21. 2021Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answeringcited by 17
  22. 2021Translate, then Parse! A strong baseline for Cross-Lingual AMR Parsingcited by 15
  23. 2018An AMR Aligner Tuned by Transition-based Parsercited by 12
  24. 2016RIGA at SemEval-2016 Task 8: Impact of Smatch Extensions and Character-Level Neural Translation on AMR Parsing Accuracycited by 11
  25. 2016Distilling an Ensemble of Greedy Dependency Parsers into One MST Parsercited by 11
  26. 2017Addressing the Data Sparsity Issue in Neural AMR Parsingcited by 11
  27. 2021Bootstrapping Multilingual AMR with Contextual Word Alignmentscited by 8

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 2; 2024: 2; 2025: 1.

8 papers.

  1. 2021Maximum Bayes Smatch Ensemble Distillation for AMR Parsingcited by 27
  2. 2023Cultural Adaptation of Recipescited by 6
  3. 2022Retrofitting Multilingual Sentence Embeddings with Abstract Meaning Representationcited by 4
  4. 2022Spanish Abstract Meaning Representation: Annotation of a General Corpuscited by 2
  5. 2023mPMR: A Multilingual Pre-trained Machine Reader at Scalecited by 2
  6. 2024Should Cross-Lingual AMR Parsing go Meta? An Empirical Assessment of Meta-Learning and Joint Learning AMR Parsingcited by 2
  7. 2025Survey of Abstract Meaning Representation: Then, Now, Futurecited by 2
  8. 2024AMR-RE: Abstract Meaning Representations for Retrieval-Based In-Context Learning in Relation Extractioncited by 0