# RelNet: End-to-End Modeling of Entities & Relations

## TL;DR

RelNet is a neural network model that performs relational reasoning by building an abstract knowledge graph of entities and their relations, trained end-to-end using question-answering supervision.

## Contribution

It introduces a memory-augmented neural network with relational memory for end-to-end relational reasoning, outperforming previous models on bAbI tasks.

## Key findings

- Solves all 20 bAbI tasks with high accuracy
- Achieves 0% error on 11 tasks
- Demonstrates effective relational reasoning capability

## Abstract

We introduce RelNet: a new model for relational reasoning. RelNet is a memory augmented neural network which models entities as abstract memory slots and is equipped with an additional relational memory which models relations between all memory pairs. The model thus builds an abstract knowledge graph on the entities and relations present in a document which can then be used to answer questions about the document. It is trained end-to-end: only supervision to the model is in the form of correct answers to the questions. We test the model on the 20 bAbI question-answering tasks with 10k examples per task and find that it solves all the tasks with a mean error of 0.3%, achieving 0% error on 11 of the 20 tasks.