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.
@article{arxiv.1905.08407,
title = {Generating Logical Forms from Graph Representations of Text and Entities},
author = {Peter Shaw and Philip Massey and Angelica Chen and Francesco Piccinno and Yasemin Altun},
journal= {arXiv preprint arXiv:1905.08407},
year = {2019}
}