mlsanityData to 7 Oct 2026

Probabilistic, Structure-Aware Algorithms for Improved Variety, Accuracy, and Coverage of AMR Alignments

arXiv 2106.06002 ↗First posted 10 Jun 2021cs.CLcited by 9

Not on the map. Why?

Abstract (arXiv)

We present algorithms for aligning components of Abstract Meaning Representation (AMR) graphs to spans in English sentences. We leverage unsupervised learning in combination with heuristics, taking the best of both worlds from previous AMR aligners. Our unsupervised models, however, are more sensitive to graph substructures, without requiring a separate syntactic parse. Our approach covers a wider variety of AMR substructures than previously considered, achieves higher coverage of nodes and edges, and does so with higher accuracy. We will release our LEAMR datasets and aligner for use in research on AMR parsing, generation, and evaluation.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 10 of its 30 references that are in the map. First posted on arXiv 10 Jun 2021.

Builds on

10 of 30 references.

References · 10

  1. 2020Stanza: A Python Natural Language Processing Toolkit for Many Human Languagescited by 719
  2. 2020AMR Parsing via Graph-Sequence Iterative Inferencecited by 47
  3. 2020Transition-based Parsing with Stack-Transformerscited by 37
  4. 2018AMR Parsing as Graph Prediction with Latent Alignmentcited by 36
  5. 2019Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learningcited by 25
  6. 2018Comprehensive Supersense Disambiguation of English Prepositions and Possessivescited by 20
  7. 2018AMR Dependency Parsing with a Typed Semantic Algebracited by 17
  8. 2018An AMR Aligner Tuned by Transition-based Parsercited by 12
  9. 2019An Improved Approach for Semantic Graph Composition with CCGcited by 2
  10. 2016Supervised Syntax-based Alignment between English Sentences and Abstract Meaning Representation Graphscited by 1

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 2; 2024: 0; 2025: 3.

9 papers.

  1. 2022Inducing and Using Alignments for Transition-based AMR Parsingcited by 11
  2. 2022Better Smatch = Better Parser? AMR evaluation is not so simple anymorecited by 9
  3. 2023Incorporating Graph Information in Transformer-based AMR Parsingcited by 7
  4. 2023AMR Parsing is Far from Solved: GrAPES, the Granular AMR Parsing Evaluation Suitecited by 6
  5. 2021Cross-linguistically Consistent Semantic and Syntactic Annotation of Child-directed Speechcited by 3
  6. 2025Survey of Abstract Meaning Representation: Then, Now, Futurecited by 2
  7. 2022Cross-lingual AMR Aligner: Paying Attention to Cross-Attentioncited by 0
  8. 2025CMV-Fuse: Cross Modal-View Fusion of AMR, Syntax, and Knowledge Representations for Aspect Based Sentiment Analysiscited by 0
  9. 2025SETUP: Sentence-level English-To-Uniform Meaning Representation Parsercited by 0