Semantic Graph Parsing with Recurrent Neural Network DAG Grammars
arXiv:1910.00051
Abstract
Semantic parses are directed acyclic graphs (DAGs), so semantic parsing should be modeled as graph prediction. But predicting graphs presents difficult technical challenges, so it is simpler and more common to predict the linearized graphs found in semantic parsing datasets using well-understood sequence models. The cost of this simplicity is that the predicted strings may not be well-formed graphs. We present recurrent neural network DAG grammars, a graph-aware sequence model that ensures only well-formed graphs while sidestepping many difficulties in graph prediction. We test our model on the Parallel Meaning Bank---a multilingual semantic graphbank. Our approach yields competitive results in English and establishes the first results for German, Italian and Dutch.
arXiv comment9 pages, to appear in EMNLP2019
References in corpus (7)
- Adam: A Method for Stochastic Optimization
- Learning Deep Generative Models of Graphs
- Learning Dependency-Based Compositional Semantics
- AMR Dependency Parsing with a Typed Semantic Algebra
- Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing
- Towards Universal Semantic Tagging
- Exploring Neural Methods for Parsing Discourse Representation Structures