Semantic Graph Parsing with Recurrent Neural Network DAG Grammars
This addresses the challenge of generating valid semantic graphs in parsing, which is crucial for natural language processing applications, though it is incremental in improving graph-aware modeling.
The paper tackled the problem of predicting semantic parses as directed acyclic graphs (DAGs) by introducing recurrent neural network DAG grammars, which ensure well-formed graphs while avoiding complexities in graph prediction. The model achieved competitive results in English and established first results for German, Italian, and Dutch on the Parallel Meaning Bank.
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.