Memory Networks
This work addresses the problem of enhancing reasoning and knowledge retention in AI systems for tasks like question answering, representing a novel paradigm rather than an incremental improvement.
The authors introduced memory networks, a new class of learning models that combine inference components with a long-term memory for reading and writing to improve prediction, and demonstrated their effectiveness in question answering tasks, showing reasoning capabilities by chaining multiple sentences to answer complex questions.
We describe a new class of learning models called memory networks. Memory networks reason with inference components combined with a long-term memory component; they learn how to use these jointly. The long-term memory can be read and written to, with the goal of using it for prediction. We investigate these models in the context of question answering (QA) where the long-term memory effectively acts as a (dynamic) knowledge base, and the output is a textual response. We evaluate them on a large-scale QA task, and a smaller, but more complex, toy task generated from a simulated world. In the latter, we show the reasoning power of such models by chaining multiple supporting sentences to answer questions that require understanding the intension of verbs.