Finding ReMO (Related Memory Object): A Simple Neural Architecture for Text based Reasoning
This work addresses relational reasoning in QA for AI systems, but it is incremental as it builds on existing Memory Network and Relation Network components.
The paper tackles text-based question answering requiring relational reasoning by introducing a neural architecture that uses MLP to find relevant information in Memory Networks, achieving new state-of-the-art results on bAbI-10k story-based and dialog-based QA tasks.
To solve the text-based question and answering task that requires relational reasoning, it is necessary to memorize a large amount of information and find out the question relevant information from the memory. Most approaches were based on external memory and four components proposed by Memory Network. The distinctive component among them was the way of finding the necessary information and it contributes to the performance. Recently, a simple but powerful neural network module for reasoning called Relation Network (RN) has been introduced. We analyzed RN from the view of Memory Network, and realized that its MLP component is able to reveal the complicate relation between question and object pair. Motivated from it, we introduce which uses MLP to find out relevant information on Memory Network architecture. It shows new state-of-the-art results in jointly trained bAbI-10k story-based question answering tasks and bAbI dialog-based question answering tasks.