Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning


Nov 03, 2017 (modified: Nov 03, 2017) ICLR 2018 Conference Blind Submission readers: everyone Show Bibtex
  • Abstract: Knowledge bases (KB), both automatically and manually constructed, are often incomplete --- many valid facts can be inferred from the KB by synthesizing existing information. We propose a new algorithm, MINERVA, that infers facts represented implicitly in a KB to solve a practical query answering task involving predicting which entity is the answer to a question. MINERVA is based on neural reinforcement learning and learns how to navigate the graph to find predictive paths. Empirically, MINERVA obtains state-of-the-art results on seven KB datasets, significantly outperforming prior methods.
  • TL;DR: We present a RL agent \textsc{minerva} which learns to walk on a knowledge graph and answer queries
  • Keywords: Knowledge Graphs, Reinforcement Learning, Query Answering