Deep Multitask Learning for Semantic Dependency Parsing
This work addresses semantic parsing for natural language processing, offering incremental advances through multitask learning approaches.
The paper tackles semantic dependency parsing by introducing a deep neural architecture that parses sentences into three formalisms, achieving a new state of the art with significant improvements without hand-engineered features or syntax.
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.