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

2018/02/06 by Matteo Grella, Grella, Matteo, Simone Cangialosi +1
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1802.02116

openalex publication_date 2018/02/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Neural Machine Translation by Jointly Learning to Align and Translate
• Dependency Parsing as Head Selection
• Recurrent Additive Networks
• Training with Exploration Improves a Greedy Stack-LSTM Parser
• Transition-Based Dependency Parsing with Stack Long Short-Term Memory

Related

• Dependency Parsing as Head Selection
• Semi-supervised Autoencoding Projective Dependency Parsing
• Headed-Span-Based Projective Dependency Parsing
• Deep Multitask Learning for Semantic Dependency Parsing
• Transition-Based Dependency Parsing using Perceptron Learner