Deep Multitask Learning for Semantic Dependency Parsing

TL;DR

This paper introduces a deep neural network architecture for semantic dependency parsing that improves state-of-the-art results by employing multitask learning approaches without relying on hand-engineered features.

Contribution

It proposes a novel deep learning model with multitask learning strategies that enhance semantic dependency parsing performance across multiple formalism representations.

Findings

Significant improvement over previous state-of-the-art results.

Multitask learning approaches enhance performance across formalism types.

Open-source code is available for replication and further research.

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.