AMR Parsing via Graph-Sequence Iterative Inference

ACL 2020  ·  Deng Cai, Wai Lam ·

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 \textit{sequence} to abstract; and (2) where in the output \textit{graph} 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 \textsc{Smatch} 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).

PDF Abstract ACL 2020 PDF ACL 2020 Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
AMR Parsing LDC2014T12 AMR Parsing via Graph-Sequence Iterative Inference F1 Full 75.4 # 3
AMR Parsing LDC2017T10 Cai and Lam Smatch 80.2 # 17