Building Dynamic Knowledge Graphs from Text-based Games
2019-10-21Code Available0· sign in to hype
Mikuláš Zelinka, Xingdi Yuan, Marc-Alexandre Côté, Romain Laroche, Adam Trischler
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/MikulasZelinka/textworld_kg_datasetOfficialIn papernone★ 0
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.