English

Building Dynamic Knowledge Graphs from Text-based Games

Computation and Language 2020-01-27 v3 Machine Learning

Abstract

We are interested in learning how to update Knowledge Graphs (KG) from text. In this preliminary work, we propose a novel Sequence-to-Sequence (Seq2Seq) architecture to generate elementary KG operations. Furthermore, we introduce a new dataset for KG extraction built upon text-based game transitions (over 300k data points). We conduct experiments and discuss the results.

Keywords

Cite

@article{arxiv.1910.09532,
  title  = {Building Dynamic Knowledge Graphs from Text-based Games},
  author = {Mikuláš Zelinka and Xingdi Yuan and Marc-Alexandre Côté and Romain Laroche and Adam Trischler},
  journal= {arXiv preprint arXiv:1910.09532},
  year   = {2020}
}

Comments

NeurIPS 2019, Graph Representation Learning (GRL) Workshop