Log In Sign Up

Strictly Breadth-First AMR Parsing

by   Chen Yu, et al.

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 encourage the model to produce the AMR graph in breadth-first order, but cannot guarantee this. To solve this problem, we propose a new architecture that guarantees that the parsing will strictly follow the breadth-first order. In each parsing step, we introduce a 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.


page 1

page 2

page 3

page 4


Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing

This paper proposes a neural semantic parsing approach -- Sequence-to-Ac...

A Graph-Based Neural Model for End-to-End Frame Semantic Parsing

Frame semantic parsing is a semantic analysis task based on FrameNet whi...

Screen Parsing: Towards Reverse Engineering of UI Models from Screenshots

Automated understanding of user interfaces (UIs) from their pixels can i...

Improving Semantic Parsing with Neural Generator-Reranker Architecture

Semantic parsing is the problem of deriving machine interpretable meanin...

ABCD: A Graph Framework to Convert Complex Sentences to a Covering Set of Simple Sentences

Atomic clauses are fundamental text units for understanding complex sent...

Towards Better Compressed Representations

We introduce the problem of computing a parsing where each phrase is of ...