Non-Projective Dependency Parsing via Latent Heads Representation (LHR)

02/06/2018
by   Matteo Grella, et al.
0

In this paper, we introduce a novel approach based on a bidirectional recurrent autoencoder to perform globally optimized non-projective dependency parsing via semi-supervised learning. The syntactic analysis is completed at the end of the neural process that generates a Latent Heads Representation (LHR), without any algorithmic constraint and with a linear complexity. The resulting "latent syntactic structure" can be used directly in other semantic tasks. The LHR is transformed into the usual dependency tree computing a simple vectors similarity. We believe that our model has the potential to compete with much more complex state-of-the-art parsing architectures.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/18/2019

Concurrent Parsing of Constituency and Dependency

Constituent and dependency representation for syntactic structure share ...
research
07/25/2018

Differentiable Perturb-and-Parse: Semi-Supervised Parsing with a Structured Variational Autoencoder

Human annotation for syntactic parsing is expensive, and large resources...
research
06/11/2017

Generic Axiomatization of Families of Noncrossing Graphs in Dependency Parsing

We present a simple encoding for unlabeled noncrossing graphs and show h...
research
03/14/2016

Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations

We present a simple and effective scheme for dependency parsing which is...
research
06/08/2021

Learning compositional structures for semantic graph parsing

AM dependency parsing is a method for neural semantic graph parsing that...
research
04/17/2018

ListOps: A Diagnostic Dataset for Latent Tree Learning

Latent tree learning models learn to parse a sentence without syntactic ...
research
09/27/2017

An attentive neural architecture for joint segmentation and parsing and its application to real estate ads

In this paper we develop a relatively simple and effective neural joint ...

Please sign up or login with your details

Forgot password? Click here to reset