Deep Multitask Learning for Semantic Dependency Parsing

2017/04/22 by Hao Peng, Peng, Hao, Sam Thomson +3 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1704.06855

openalex publication_date 2017/04/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We present a deep neural architecture that parses sentences into three semantic dependency graph formalisms. By using efficient, nearly arc-factored inference and a bidirectional-LSTM composed with a multi-layer perceptron, our base system is able to significantly improve the state of the art for semantic dependency parsing, without using hand-engineered features or syntax. We then explore two multitask learning approaches---one that shares parameters across formalisms, and one that uses higher-order structures to predict the graphs jointly. We find that both approaches improve performance across formalisms on average, achieving a new state of the art. Our code is open-source and available at https://github.com/Noahs-ARK/NeurboParser.

Citations

• Tensor Decompositions and Applications
• Long Short-Term Memory
• Bidirectional recurrent neural networks
• Natural Language Understanding with Distributed Representation
• Neural Probabilistic Model for Non-projective MST Parsing

Cited by

• Dependency Parsing is More Parameter-Efficient with Normalization

Related

• Second-Order Semantic Dependency Parsing with End-to-End Neural Networks
• Simpler but More Accurate Semantic Dependency Parsing
• A Higher-Order Semantic Dependency Parser
• Learning compositional structures for semantic graph parsing
• Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First Strategies