# AMR Parsing via Graph-Sequence Iterative Inference

arXiv: https://arxiv.org/abs/2004.05572 · HTML: https://mlsanity.com/paper/2004.05572/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Apr 2020.

## Built on by (most cited first, 30 of 47)

- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [Graph Pre-training for AMR Parsing and Generation](https://mlsanity.com/paper/2203.07836/) (2022)
- [FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations](https://mlsanity.com/paper/2204.06508/) (2022)
- [Maximum Bayes Smatch Ensemble Distillation for AMR Parsing](https://mlsanity.com/paper/2112.07790/) (2021)
- [AMR Parsing with Action-Pointer Transformer](https://mlsanity.com/paper/2104.14674/) (2021)
- [Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsing](https://mlsanity.com/paper/2110.15534/) (2021)
- [Semantic Representation for Dialogue Modeling](https://mlsanity.com/paper/2105.10188/) (2021)
- [SMATCH++: Standardized and Extended Evaluation of Semantic Graphs](https://mlsanity.com/paper/2305.06993/) (2023)
- [Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering](https://mlsanity.com/paper/2105.11776/) (2021)
- [Translate, then Parse! A strong baseline for Cross-Lingual AMR Parsing](https://mlsanity.com/paper/2106.04565/) (2021)
- [Exploiting Reasoning Chains for Multi-hop Science Question Answering](https://mlsanity.com/paper/2109.02905/) (2021)
- [Ensembling Graph Predictions for AMR Parsing](https://mlsanity.com/paper/2110.09131/) (2021)
- [BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing](https://mlsanity.com/paper/2206.10668/) (2022)
- [Interpretable AMR-Based Question Decomposition for Multi-hop Question Answering](https://mlsanity.com/paper/2206.08486/) (2022)
- [ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation](https://mlsanity.com/paper/2305.16585/) (2023)
- [Hierarchical Curriculum Learning for AMR Parsing](https://mlsanity.com/paper/2110.07855/) (2021)
- [A Double-Graph Based Framework for Frame Semantic Parsing](https://mlsanity.com/paper/2206.09158/) (2022)
- [Improving Medical Dialogue Generation with Abstract Meaning Representations](https://mlsanity.com/paper/2309.10608/) (2023)
- [Probabilistic, Structure-Aware Algorithms for Improved Variety, Accuracy, and Coverage of AMR Alignments](https://mlsanity.com/paper/2106.06002/) (2021)
- [Better Smatch = Better Parser? AMR evaluation is not so simple anymore](https://mlsanity.com/paper/2210.06461/) (2022)
- [Multilingual AMR Parsing with Noisy Knowledge Distillation](https://mlsanity.com/paper/2109.15196/) (2021)
- [Incorporating Graph Information in Transformer-based AMR Parsing](https://mlsanity.com/paper/2306.13467/) (2023)
- [T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation](https://mlsanity.com/paper/2212.01667/) (2022)
- [AMR Parsing is Far from Solved: GrAPES, the Granular AMR Parsing Evaluation Suite](https://mlsanity.com/paper/2312.03480/) (2023)
- [Every Answer Matters: Evaluating Commonsense with Probabilistic Measures](https://mlsanity.com/paper/2406.04145/) (2024)
- [ATP: AMRize Then Parse! Enhancing AMR Parsing with PseudoAMRs](https://mlsanity.com/paper/2204.08875/) (2022)
- [Retrofitting Multilingual Sentence Embeddings with Abstract Meaning Representation](https://mlsanity.com/paper/2210.09773/) (2022)
- [Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representations](https://mlsanity.com/paper/2211.00881/) (2022)
- [One Semantic Parser to Parse Them All: Sequence to Sequence Multi-Task Learning on Semantic Parsing Datasets](https://mlsanity.com/paper/2106.04476/) (2021)
- [Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation](https://mlsanity.com/paper/2109.03808/) (2021)

## Abstract (arXiv)

We propose a new end-to-end model that treats AMR parsing as a series of dual decisions on the input sequence and the incrementally constructed graph. At each time step, our model performs multiple rounds of attention, reasoning, and composition that aim to answer two critical questions: (1) which part of the input textitsequence to abstract; and (2) where in the output textitgraph to construct the new concept. We show that the answers to these two questions are mutually causalities. We design a model based on iterative inference that helps achieve better answers in both perspectives, leading to greatly improved parsing accuracy. Our experimental results significantly outperform all previously reported textscSmatch scores by large margins. Remarkably, without the help of any large-scale pre-trained language model (e.g., BERT), our model already surpasses previous state-of-the-art using BERT. With the help of BERT, we can push the state-of-the-art results to 80.2% on LDC2017T10 (AMR 2.0) and 75.4% on LDC2014T12 (AMR 1.0).