Non-Projective Dependency Parsing via Latent Heads Representation (LHR)
This addresses syntactic parsing for natural language processing, offering a simpler and efficient alternative to complex architectures.
The paper tackles non-projective dependency parsing by introducing a bidirectional recurrent autoencoder to generate a Latent Heads Representation (LHR) with linear complexity, achieving competitive performance with state-of-the-art methods.
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.