Strictly Breadth-First AMR Parsing
This work addresses a specific limitation in AMR parsing for NLP researchers, offering an incremental improvement over existing breadth-first methods.
The paper tackles the problem of ensuring strict breadth-first order in AMR parsing, proposing a new architecture that guarantees this order and achieves better performance on AMR 1.0 and 2.0 datasets.
AMR parsing is the task that maps a sentence to an AMR semantic graph automatically. We focus on the breadth-first strategy of this task, which was proposed recently and achieved better performance than other strategies. However, current models under this strategy only \emph{encourage} the model to produce the AMR graph in breadth-first order, but \emph{cannot guarantee} this. To solve this problem, we propose a new architecture that \emph{guarantees} that the parsing will strictly follow the breadth-first order. In each parsing step, we introduce a \textbf{focused parent} vertex and use this vertex to guide the generation. With the help of this new architecture and some other improvements in the sentence and graph encoder, our model obtains better performance on both the AMR 1.0 and 2.0 dataset.