# Hierarchical Curriculum Learning for AMR Parsing

arXiv: https://arxiv.org/abs/2110.07855 · HTML: https://mlsanity.com/paper/2110.07855/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 36 references that are in the map.
- First posted on arXiv 15 Oct 2021.

## Builds on (most cited first, 18 of 18)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [Competence-based Curriculum Learning for Neural Machine Translation](https://mlsanity.com/paper/1903.09848/) (2019)
- [AMR Parsing as Sequence-to-Graph Transduction](https://mlsanity.com/paper/1905.08704/) (2019)
- [AMR Parsing via Graph-Sequence Iterative Inference](https://mlsanity.com/paper/2004.05572/) (2020)
- [Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/1911.08717/) (2019)
- [Transition-based Parsing with Stack-Transformers](https://mlsanity.com/paper/2010.10669/) (2020)
- [AMR Parsing as Graph Prediction with Latent Alignment](https://mlsanity.com/paper/1805.05286/) (2018)
- [Abstract Meaning Representation for Multi-Document Summarization](https://mlsanity.com/paper/1806.05655/) (2018)
- [An Incremental Parser for Abstract Meaning Representation](https://mlsanity.com/paper/1608.06111/) (2016)
- [Broad-Coverage Semantic Parsing as Transduction](https://mlsanity.com/paper/1909.02607/) (2019)
- [Improving AMR Parsing with Sequence-to-Sequence Pre-training](https://mlsanity.com/paper/2010.01771/) (2020)
- [Dialogue Response Selection with Hierarchical Curriculum Learning](https://mlsanity.com/paper/2012.14756/) (2020)
- [Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning](https://mlsanity.com/paper/1905.13370/) (2019)
- [AMR Parsing with Action-Pointer Transformer](https://mlsanity.com/paper/2104.14674/) (2021)
- [Guided Neural Language Generation for Abstractive Summarization using Abstract Meaning Representation](https://mlsanity.com/paper/1808.09160/) (2018)
- [Core Semantic First: A Top-down Approach for AMR Parsing](https://mlsanity.com/paper/1909.04303/) (2019)
- [Pushing the Limits of AMR Parsing with Self-Learning](https://mlsanity.com/paper/2010.10673/) (2020)

## Built on by (most cited first, 10 of 10)

- [Let's Learn Step by Step: Enhancing In-Context Learning Ability with Curriculum Learning](https://mlsanity.com/paper/2402.10738/) (2024)
- [CLNode: Curriculum Learning for Node Classification](https://mlsanity.com/paper/2206.07258/) (2022)
- [A Two-Stream AMR-enhanced Model for Document-level Event Argument Extraction](https://mlsanity.com/paper/2205.00241/) (2022)
- [Public Wisdom Matters! Discourse-Aware Hyperbolic Fourier Co-Attention for Social-Text Classification](https://mlsanity.com/paper/2209.13017/) (2022)
- [HiCuLR: Hierarchical Curriculum Learning for Rhetorical Role Labeling of Legal Documents](https://mlsanity.com/paper/2409.18647/) (2024)
- [ATP: AMRize Then Parse! Enhancing AMR Parsing with PseudoAMRs](https://mlsanity.com/paper/2204.08875/) (2022)
- [AMR Parsing with Causal Hierarchical Attention and Pointers](https://mlsanity.com/paper/2310.11964/) (2023)
- [A Two-Stage Method for Chinese AMR Parsing](https://mlsanity.com/paper/2209.14512/) (2022)
- [Guiding AMR Parsing with Reverse Graph Linearization](https://mlsanity.com/paper/2310.08860/) (2023)
- [Disentangling Curriculum Learning in NLP: Towards a Unifying Taxonomy](https://mlsanity.com/paper/2607.18984/) (2026)

## Abstract (arXiv)

Abstract Meaning Representation (AMR) parsing aims to translate sentences to semantic representation with a hierarchical structure, and is recently empowered by pretrained sequence-to-sequence models. However, there exists a gap between their flat training objective (i.e., equally treats all output tokens) and the hierarchical AMR structure, which limits the model generalization. To bridge this gap, we propose a Hierarchical Curriculum Learning (HCL) framework with Structure-level (SC) and Instance-level Curricula (IC). SC switches progressively from core to detail AMR semantic elements while IC transits from structure-simple to -complex AMR instances during training. Through these two warming-up processes, HCL reduces the difficulty of learning complex structures, thus the flat model can better adapt to the AMR hierarchy. Extensive experiments on AMR2.0, AMR3.0, structure-complex and out-of-distribution situations verify the effectiveness of HCL.