Generating Logical Forms from Graph Representations of Text and Entities
Peter Martin Shaw, Philip Massey, Angelica Chen, Francesco Piccinno, Yasemin Altün · 2019
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 stateof-the-art across several tasks without pretraining, and outperforms existing approaches when combined with BERT pre-training.