mlsanityData to 7 Oct 2026

Cross-lingual AMR Aligner: Paying Attention to Cross-Attention

arXiv 2206.07587 ↗First posted 15 Jun 2022cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper introduces a novel aligner for Abstract Meaning Representation (AMR) graphs that can scale cross-lingually, and is thus capable of aligning units and spans in sentences of different languages. Our approach leverages modern Transformer-based parsers, which inherently encode alignment information in their cross-attention weights, allowing us to extract this information during parsing. This eliminates the need for English-specific rules or the Expectation Maximization (EM) algorithm that have been used in previous approaches. In addition, we propose a guided supervised method using alignment to further enhance the performance of our aligner. We achieve state-of-the-art results in the benchmarks for AMR alignment and demonstrate our aligner's ability to obtain them across multiple languages. Our code will be available at hrefhttps://www.github.com/Babelscape/AMR-alignmentgithub.com/Babelscape/AMR-alignment.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 55 references that are in the map. First posted on arXiv 15 Jun 2022.

Builds on

33 of 55 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  4. 2018Deep contextualized word representationscited by 2,285
  5. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  6. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  7. 2019BERT Rediscovers the Classical NLP Pipelinecited by 1,046
  8. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
  9. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  10. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 542
  11. 2016From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classificationcited by 337
  12. 2021Word Alignment by Fine-tuning Embeddings on Parallel Corporacited by 186
21 more
  1. 2020The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?cited by 122
  2. 2019Attention Interpretability Across NLP Taskscited by 71
  3. 2022Graph Pre-training for AMR Parsing and Generationcited by 55
  4. 2020Leveraging Abstract Meaning Representation for Knowledge Base Question Answeringcited by 53
  5. 2020Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attentioncited by 45
  6. 2019Semantic Neural Machine Translation using AMRcited by 37
  7. 2018Abstract Meaning Representation for Multi-Document Summarizationcited by 35
  8. 2021Supervising Model Attention with Human Explanations for Robust Natural Language Inferencecited by 29
  9. 2021Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsingcited by 25
  10. 2018Guided Neural Language Generation for Abstractive Summarization using Abstract Meaning Representationcited by 24
  11. 2021Long-Span Summarization via Local Attention and Content Selectioncited by 24
  12. 2021Do Context-Aware Translation Models Pay the Right Attention?cited by 21
  13. 2020Mask-Align: Self-Supervised Neural Word Alignmentcited by 20
  14. 2017Cross-lingual Abstract Meaning Representation Parsingcited by 19
  15. 2021Modeling Concentrated Cross-Attention for Neural Machine Translation with Gaussian Mixture Modelcited by 18
  16. 2021Translate, then Parse! A strong baseline for Cross-Lingual AMR Parsingcited by 15
  17. 2020Guiding Attention for Self-Supervised Learning with Transformerscited by 14
  18. 2018An AMR Aligner Tuned by Transition-based Parsercited by 12
  19. 2020I Know What You Asked: Graph Path Learning using AMR for Commonsense Reasoningcited by 10
  20. 2020Structured Self-Attention Weights Encode Semantics in Sentiment Analysiscited by 9
  21. 2021Probabilistic, Structure-Aware Algorithms for Improved Variety, Accuracy, and Coverage of AMR Alignmentscited by 9

Built on by

Not cited yet.