Memory Networks

By Jason Aaron Edward Weston, Sumit Chopra, Antoine Bordes. 2014

1,867 citations recorded by the source corpus.

Abstract: 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.

Subfields: Electrical and Electronic Engineering, Retrieval-Augmented Generation, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Electrical and Electronic Engineering

  1. Yoshua Bengio
  2. J. Urgen Schmidhuber
  3. Sergey Levine
  4. Yuxi Li
  5. Oriol Vinyals
  6. Joelle Pineau
  7. Razvan Pascanu
  8. Timothy P. Lillicrap

In Retrieval-Augmented Generation

  1. Hannaneh Hajishirzi
  2. Sebastian Riedel
  3. Danqi Chen
  4. Jason Aaron Edward Weston
  5. Wen-tau Yih
  6. William W. Cohen
  7. Minjoon Seo
  8. Jianfeng Gao

In Natural Language Processing

  1. Mohit Bansal
  2. Jianfeng Gao
  3. Luke S. Zettlemoyer
  4. Jason Aaron Edward Weston
  5. Kyunghyun Cho
  6. Percy Liang
  7. Yejin Choi
  8. Graham Neubig

Citations in the corpus