Methods > General > Working Memory Models

Dynamic Memory Network

Introduced by Kumar et al. in Ask Me Anything: Dynamic Memory Networks for Natural Language Processing

A Dynamic Memory Network is a neural network architecture which processes input sequences and questions, forms episodic memories, and generates relevant answers. Questions trigger an iterative attention process which allows the model to condition its attention on the inputs and the result of previous iterations. These results are then reasoned over in a hierarchical recurrent sequence model to generate answers.

The DMN consists of a number of modules:

  • Input Module: The input module encodes raw text inputs from the task into distributed vector representations. The input takes forms like a sentence, a long story, a movie review and so on.
  • Question Module: The question module encodes the question of the task into a distributed vector representation. For question answering, the question may be a sentence such as "Where did the author first fly?". The representation is fed into the episodic memory module, and forms the basis, or initial state, upon which the episodic memory module iterates.
  • Episodic Memory Module: Given a collection of input representations, the episodic memory module chooses which parts of the inputs to focus on through the attention mechanism. It then produces a ”memory” vector representation taking into account the question as well as the previous memory. Each iteration provides the module with newly relevant information about the input. In other words, the module has the ability to retrieve new information, in the form of input representations, which were thought to be irrelevant in previous iterations.
  • Answer Module: The answer module generates an answer from the final memory vector of the memory module.
Source: Ask Me Anything: Dynamic Memory Networks for Natural Language Processing

Latest Papers

Contextualize Knowledge Bases with Transformer for End-to-end Task-Oriented Dialogue Systems
Yanjie GouYinjie LeiLingqiao Liu
Doctor2Vec: Dynamic Doctor Representation Learning for Clinical Trial Recruitment
Siddharth BiswalCao XiaoLucas M. GlassElizabeth MilkovitsJimeng Sun
Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection
| Shumin DengNingyu ZhangJiaojian KangYichi ZhangWei zhangHuajun Chen
Entropy-Enhanced Multimodal Attention Model for Scene-Aware Dialogue Generation
Kuan-Yen LinChao-Chun HsuYun-Nung ChenLun-Wei Ku
Visual Tracking via Dynamic Memory Networks
Tianyu YangAntoni B. Chan
Exploiting Contextual Information via Dynamic Memory Network for Event Detection
| Shaobo LiuRui ChengXiaoming YuXue-Qi Cheng
Relational dynamic memory networks
Trang PhamTruyen TranSvetha Venkatesh
Motion-Appearance Co-Memory Networks for Video Question Answering
Jiyang GaoRunzhou GeKan ChenRam Nevatia
Learning Dynamic Memory Networks for Object Tracking
| Tianyu YangAntoni B. Chan
Integrating Order Information and Event Relation for Script Event Prediction
Zhongqing WangYue ZhangChing-Yun Chang
Ask Me Even More: Dynamic Memory Tensor Networks (Extended Model)
| Govardana Sachithanandam RamachandranAjay Sohmshetty
Dynamic Memory Networks for Visual and Textual Question Answering
| Caiming XiongStephen MerityRichard Socher
Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
| Ankit KumarOzan .IrsoyPeter OndruskaMohit IyyerJames BradburyIshaan GulrajaniVictor ZhongRomain PaulusRichard Socher