mlsanityData to 7 Oct 2026

ATP: AMRize Then Parse! Enhancing AMR Parsing with PseudoAMRs

arXiv 2204.08875 ↗First posted 19 Apr 2022cs.CL cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

As Abstract Meaning Representation (AMR) implicitly involves compound semantic annotations, we hypothesize auxiliary tasks which are semantically or formally related can better enhance AMR parsing. We find that 1) Semantic role labeling (SRL) and dependency parsing (DP), would bring more performance gain than other tasks e.g. MT and summarization in the text-to-AMR transition even with much less data. 2) To make a better fit for AMR, data from auxiliary tasks should be properly "AMRized" to PseudoAMR before training. Knowledge from shallow level parsing tasks can be better transferred to AMR Parsing with structure transform. 3) Intermediate-task learning is a better paradigm to introduce auxiliary tasks to AMR parsing, compared to multitask learning. From an empirical perspective, we propose a principled method to involve auxiliary tasks to boost AMR parsing. Extensive experiments show that our method achieves new state-of-the-art performance on different benchmarks especially in topology-related scores.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 24 of its 49 references that are in the map. First posted on arXiv 19 Apr 2022.

Builds on

24 of 49 references.

References · 24

  1. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  2. 2015Teaching Machines to Read and Comprehendcited by 1,039
  3. 2017A Survey on Multi-Task Learningcited by 838
  4. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  5. 2021DialogSum: A Real-Life Scenario Dialogue Summarization Datasetcited by 181
  6. 2020Intermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work?cited by 127
  7. 2020Efficient One-Pass End-to-End Entity Linking for Questionscited by 76
  8. 2021What to Pre-Train on? Efficient Intermediate Task Selectioncited by 62
  9. 2019AMR Parsing as Sequence-to-Graph Transductioncited by 50
  10. 2020AMR Parsing via Graph-Sequence Iterative Inferencecited by 47
  11. 2020Transition-based Parsing with Stack-Transformerscited by 37
  12. 2018AMR Parsing as Graph Prediction with Latent Alignmentcited by 36
12 more
  1. 2018Abstract Meaning Representation for Multi-Document Summarizationcited by 35
  2. 2016An Incremental Parser for Abstract Meaning Representationcited by 34
  3. 2019Broad-Coverage Semantic Parsing as Transductioncited by 32
  4. 2020Improving AMR Parsing with Sequence-to-Sequence Pre-trainingcited by 30
  5. 2019Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learningcited by 25
  6. 2021AMR Parsing with Action-Pointer Transformercited by 25
  7. 2021Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsingcited by 25
  8. 2018Guided Neural Language Generation for Abstractive Summarization using Abstract Meaning Representationcited by 24
  9. 2020Pushing the Limits of AMR Parsing with Self-Learningcited by 16
  10. 2021Ensembling Graph Predictions for AMR Parsingcited by 15
  11. 2021Hierarchical Curriculum Learning for AMR Parsingcited by 10
  12. 2021One Semantic Parser to Parse Them All: Sequence to Sequence Multi-Task Learning on Semantic Parsing Datasetscited by 3

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3.

5 papers.

  1. 2022A Two-Stream AMR-enhanced Model for Document-level Event Argument Extractioncited by 16
  2. 2023Incorporating Graph Information in Transformer-based AMR Parsingcited by 7
  3. 2023AMRs Assemble! Learning to Ensemble with Autoregressive Models for AMR Parsingcited by 3
  4. 2022A Two-Stage Method for Chinese AMR Parsingcited by 0
  5. 2023Guiding AMR Parsing with Reverse Graph Linearizationcited by 0