AMR Parsing with Causal Hierarchical Attention and Pointers
Not on the map. Why?
Abstract (arXiv)
Translation-based AMR parsers have recently gained popularity due to their simplicity and effectiveness. They predict linearized graphs as free texts, avoiding explicit structure modeling. However, this simplicity neglects structural locality in AMR graphs and introduces unnecessary tokens to represent coreferences. In this paper, we introduce new target forms of AMR parsing and a novel model, CHAP, which is equipped with causal hierarchical attention and the pointer mechanism, enabling the integration of structures into the Transformer decoder. We empirically explore various alternative modeling options. Experiments show that our model outperforms baseline models on four out of five benchmarks in the setting of no additional data.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 29 of its 47 references that are in the map. First posted on arXiv 18 Oct 2023.
Builds on
29 of 47 references.
References · 29
- 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
- 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
- 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
- 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,292
- 2015Pointer Networkscited by 895
- 2013One Billion Word Benchmark for Measuring Progress in Statistical Language Modelingcited by 308
- 2015Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networkscited by 306
- 2016Recurrent Neural Network Grammarscited by 109
- 2019Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Autoencoderscited by 60
- 2017Neural AMR: Sequence-to-Sequence Models for Parsing and Generationcited by 56
- 2022Graph Pre-training for AMR Parsing and Generationcited by 55
- 2020AMR Parsing via Graph-Sequence Iterative Inferencecited by 47
17 more
- 2022Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scalecited by 41
- 2020Transition-based Parsing with Stack-Transformerscited by 38
- 2016An Incremental Parser for Abstract Meaning Representationcited by 34
- 2020Improving AMR Parsing with Sequence-to-Sequence Pre-trainingcited by 30
- 2019Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learningcited by 25
- 2021AMR Parsing with Action-Pointer Transformercited by 25
- 2021Structural Guidance for Transformer Language Modelscited by 25
- 2021Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsingcited by 25
- 2018Guided Neural Language Generation for Abstractive Summarization using Abstract Meaning Representationcited by 24
- 2019Core Semantic First: A Top-down Approach for AMR Parsingcited by 24
- 2021Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networkscited by 21
- 2017Towards String-to-Tree Neural Machine Translationcited by 19
- 2021R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modelingcited by 19
- 2017AMR Parsing using Stack-LSTMscited by 15
- 2021Hierarchical Curriculum Learning for AMR Parsingcited by 10
- 2021A Conditional Splitting Framework for Efficient Constituency Parsingcited by 7
- 2023Incorporating Graph Information in Transformer-based AMR Parsingcited by 7
Built on by
Citing papers per year: 2024: 1.
1 paper.