Deep Multitask Learning for Semantic Dependency Parsing
arXiv:1704.06855
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.
Proceedings of ACL 2017
References in corpus (4)
Cited by in corpus (14)
- Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold
- Robust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information
- Semi-Supervised Sequence Modeling with Cross-View Training
- Multi-task Learning for Universal Sentence Embeddings: A Thorough Evaluation using Transfer and Auxiliary Tasks
- Syntactic Scaffolds for Semantic Structures
- Learning Joint Semantic Parsers from Disjoint Data
- Multi-task Learning over Graph Structures
- Joint Multi-Domain Learning for Automatic Short Answer Grading
- Second-Order Semantic Dependency Parsing with End-to-End Neural Networks
- Learning Robust, Transferable Sentence Representations for Text Classification
- Learning to Multi-Task Learn for Better Neural Machine Translation
- Towards Coinductive Models for Natural Language Understanding. Bringing together Deep Learning and Deep Semantics
- Multi-Task Learning for Argumentation Mining
- Towards Explainable Fact Checking