A Transition-based Algorithm for Unrestricted AMR Parsing

05/23/2018
by   David Vilares, et al.
0

Non-projective parsing can be useful to handle cycles and reentrancy in AMR graphs. We explore this idea and introduce a greedy left-to-right non-projective transition-based parser. At each parsing configuration, an oracle decides whether to create a concept or whether to connect a pair of existing concepts. The algorithm handles reentrancy and arbitrary cycles natively, i.e. within the transition system itself. The model is evaluated on the LDC2015E86 corpus, obtaining results close to the state of the art, including a Smatch of 64

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/21/2018

Faster Shift-Reduce Constituent Parsing with a Non-Binary, Bottom-Up Strategy

We propose a novel non-binary shift-reduce algorithm for constituent par...
research
07/04/2018

Global Transition-based Non-projective Dependency Parsing

Shi, Huang, and Lee (2017) obtained state-of-the-art results for English...
research
03/20/2019

Left-to-Right Dependency Parsing with Pointer Networks

We propose a novel transition-based algorithm that straightforwardly par...
research
05/27/2019

Sequential Graph Dependency Parser

We propose a method for non-projective dependency parsing by incremental...
research
10/25/2017

Non-Projective Dependency Parsing with Non-Local Transitions

We present a novel transition system, based on the Covington non-project...
research
05/26/2023

Slide, Constrain, Parse, Repeat: Synchronous SlidingWindows for Document AMR Parsing

The sliding window approach provides an elegant way to handle contexts o...
research
02/24/2019

Unlexicalized Transition-based Discontinuous Constituency Parsing

Lexicalized parsing models are based on the assumptions that (i) constit...

Please sign up or login with your details

Forgot password? Click here to reset