Learning Joint Semantic Parsers from Disjoint Data

Abstract

We present a new approach to learning semantic parsers from multiple datasets, even when the target semantic formalisms are drastically different, and the underlying corpora do not overlap. We handle such "disjoint" data by treating annotations for unobserved formalisms as latent structured variables. Building on state-of-the-art baselines, we show improvements both in frame-semantic parsing and semantic dependency parsing by modeling them jointly.

arXiv commentNAACL 2018

References in corpus (4)

• DyNet: The Dynamic Neural Network Toolkit
• Segmental Recurrent Neural Networks
• Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold
• Deep Multitask Learning for Semantic Dependency Parsing

Cited by in corpus (4)

• Dependency or Span, End-to-End Uniform Semantic Role Labeling
• Syntactic Scaffolds for Semantic Structures
• Second-Order Semantic Dependency Parsing with End-to-End Neural Networks
• Positional Attention-based Frame Identification with BERT: A Deep Learning Approach to Target Disambiguation and Semantic Frame Selection