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

TL;DR

This paper presents a novel semi-supervised neural approach for non-projective dependency parsing using a bidirectional autoencoder to generate a latent syntactic structure, enabling efficient and flexible parsing without traditional constraints.

Contribution

Introduces a bidirectional autoencoder model that produces a latent heads representation for non-projective dependency parsing with linear complexity and broad applicability.

Findings

Achieves linear complexity in dependency parsing.

Produces latent syntactic structures usable in semantic tasks.

Potential to compete with complex state-of-the-art models.

Abstract

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.