RelNet: End-to-End Modeling of Entities & Relations
This addresses the problem of relational reasoning in AI for tasks like document-based question-answering, representing an incremental improvement over existing methods.
The paper tackles relational reasoning in question-answering by introducing RelNet, a memory-augmented neural network that models entities and relations as an abstract knowledge graph, achieving a mean error of 0.3% on the 20 bAbI tasks with 0% error on 11 tasks.
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.