Sequential Graph Dependency Parser

05/27/2019
by   Sean Welleck, et al.
2

We propose a method for non-projective dependency parsing by incrementally predicting a set of edges. Since the edges do not have a pre-specified order, we propose a set-based learning method. Our method blends graph, transition, and easy-first parsing, including a prior state of the parser as a special case. The proposed transition-based method successfully parses near the state of the art on both projective and non-projective languages, without assuming a certain parsing order.

READ FULL TEXT

page 4

page 9

page 10

research
09/15/2020

Fast semantic parsing with well-typedness guarantees

AM dependency parsing is a linguistically principled method for neural s...
research
03/18/2015

Learning to Search for Dependencies

We demonstrate that a dependency parser can be built using a credit assi...
research
02/13/2019

Leveraging Newswire Treebanks for Parsing Conversational Data with Argument Scrambling

We investigate the problem of parsing conversational data of morphologic...
research
04/17/2021

Question Decomposition with Dependency Graphs

QDMR is a meaning representation for complex questions, which decomposes...
research
06/21/2023

A Semi-Autoregressive Graph Generative Model for Dependency Graph Parsing

Recent years have witnessed the impressive progress in Neural Dependency...
research
09/28/2021

Instance-Based Neural Dependency Parsing

Interpretable rationales for model predictions are crucial in practical ...
research
05/23/2018

A Transition-based Algorithm for Unrestricted AMR Parsing

Non-projective parsing can be useful to handle cycles and reentrancy in ...

Please sign up or login with your details

Forgot password? Click here to reset