mlsanityData to 7 Oct 2026

AMR Parsing as Graph Prediction with Latent Alignment

arXiv 1805.05286 ↗First posted 14 May 2018cs.CLcited by 36

Not on the map. Why?

Abstract (arXiv)

Abstract meaning representations (AMRs) are broad-coverage sentence-level semantic representations. AMRs represent sentences as rooted labeled directed acyclic graphs. AMR parsing is challenging partly due to the lack of annotated alignments between nodes in the graphs and words in the corresponding sentences. We introduce a neural parser which treats alignments as latent variables within a joint probabilistic model of concepts, relations and alignments. As exact inference requires marginalizing over alignments and is infeasible, we use the variational auto-encoding framework and a continuous relaxation of the discrete alignments. We show that joint modeling is preferable to using a pipeline of align and parse. The parser achieves the best reported results on the standard benchmark (74.4% on LDC2016E25).

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 14; 2022: 10; 2023: 8; 2024: 1; 2025: 3.

36 papers.

Sort:

  1. 2023A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPTcited by 221
  2. 2022Graph Pre-training for AMR Parsing and Generationcited by 55
  3. 2021AMR Parsing with Action-Pointer Transformercited by 25
  4. 2021Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsingcited by 25
  5. 2021Semantic Representation for Dialogue Modelingcited by 24
  6. 2023SMATCH++: Standardized and Extended Evaluation of Semantic Graphscited by 19
  7. 2021Structured Reordering for Modeling Latent Alignments in Sequence Transductioncited by 17
  8. 2021Translate, then Parse! A strong baseline for Cross-Lingual AMR Parsingcited by 15
  9. 2021Weisfeiler-Leman in the BAMBOO: Novel AMR Graph Metrics and a Benchmark for AMR Graph Similaritycited by 15
  10. 2022Inducing and Using Alignments for Transition-based AMR Parsingcited by 11
  11. 2021Hierarchical Curriculum Learning for AMR Parsingcited by 10
  12. 2021Probabilistic, Structure-Aware Algorithms for Improved Variety, Accuracy, and Coverage of AMR Alignmentscited by 9
24 more
  1. 2022Better Smatch = Better Parser? AMR evaluation is not so simple anymorecited by 9
  2. 2021Bootstrapping Multilingual AMR with Contextual Word Alignmentscited by 8
  3. 2021A Graph-Based Neural Model for End-to-End Frame Semantic Parsingcited by 7
  4. 2021LAGr: Labeling Aligned Graphs for Improving Systematic Generalization in Semantic Parsingcited by 7
  5. 2023Incorporating Graph Information in Transformer-based AMR Parsingcited by 7
  6. 2021Grounded Graph Decoding Improves Compositional Generalization in Question Answeringcited by 6
  7. 2022ATP: AMRize Then Parse! Enhancing AMR Parsing with PseudoAMRscited by 5
  8. 2023Compositional Generalization without Trees using Multiset Tagging and Latent Permutationscited by 5
  9. 2023Structural generalization in COGS: Supertagging is (almost) all you needcited by 4
  10. 2022Semantic-based Pre-training for Dialogue Understandingcited by 3
  11. 2021Levi Graph AMR Parser using Heterogeneous Attentioncited by 2
  12. 2022Cross-domain Generalization for AMR Parsingcited by 2
  13. 2023On graph-based reentrancy-free semantic parsingcited by 2
  14. 2023SynJax: Structured Probability Distributions for JAXcited by 2
  15. 2025Survey of Abstract Meaning Representation: Then, Now, Futurecited by 2
  16. 2025DiaCDM: Cognitive Diagnosis in Teacher-Student Dialogues using the Initiation-Response-Evaluation Frameworkcited by 2
  17. 2021Making Better Use of Bilingual Information for Cross-Lingual AMR Parsingcited by 1
  18. 2024Adapting Abstract Meaning Representation Parsing to the Clinical Narrative -- the SPRING THYME parsercited by 1
  19. 2022SMARAGD: Learning SMatch for Accurate and Rapid Approximate Graph Distancecited by 0
  20. 2022LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic Parsingcited by 0
  21. 2022Transition-based Abstract Meaning Representation Parsing with Contextual Embeddingscited by 0
  22. 2022Strictly Breadth-First AMR Parsingcited by 0
  23. 2023Guiding AMR Parsing with Reverse Graph Linearizationcited by 0
  24. 2025Evaluation of Finetuned LLMs in AMR Parsingcited by 0