Generating Logical Forms from Graph Representations of Text and Entities

2019/05/21 by Peter Shaw, Philip Massey, Shaw, Peter +8 · 4 citations
Computer Science · #Advanced Graph Neural Networks #Natural Language Processing Techniques #Topic Modeling #cs.CL

paper · pdf · doi:10.48550/arxiv.1905.08407

ACL 2019

arxiv created 2019/09/25 · arxiv updated 2019/09/27

Abstract

Structured information about entities is critical for many semantic parsing tasks. We present an approach that uses a Graph Neural Network (GNN) architecture to incorporate information about relevant entities and their relations during parsing. Combined with a decoder copy mechanism, this approach provides a conceptually simple mechanism to generate logical forms with entities. We demonstrate that this approach is competitive with the state-of-the-art across several tasks without pre-training, and outperforms existing approaches when combined with BERT pre-training.

Cited by

• Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures
• Improving Semantic Parsing with Neural Generator-Reranker Architecture
• Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base
• ETC: Encoding Long and Structured Inputs in Transformers

Related

• Language Independent Neuro-Symbolic Semantic Parsing for Form Understanding
• Learning an Executable Neural Semantic Parser
• Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model
• Language to Logical Form with Neural Attention
• A Higher-Order Semantic Dependency Parser