# Ask Me Anything: Dynamic Memory Networks for Natural Language Processing

arXiv: https://arxiv.org/abs/1506.07285 · HTML: https://mlsanity.com/paper/1506.07285/

## Key facts

- Cited by 117 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jun 2015.

## Built on by (most cited first, 30 of 117)

- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization](https://mlsanity.com/paper/2212.12017/) (2022)
- [Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer](https://mlsanity.com/paper/2102.09550/) (2021)
- [Advances and Challenges in Conversational Recommender Systems: A Survey](https://mlsanity.com/paper/2101.09459/) (2021)
- [MeMOT: Multi-Object Tracking with Memory](https://mlsanity.com/paper/2203.16761/) (2022)
- [Training Language Models with Memory Augmentation](https://mlsanity.com/paper/2205.12674/) (2022)
- [MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection](https://mlsanity.com/paper/2103.04224/) (2021)
- [LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5](https://mlsanity.com/paper/2110.07298/) (2021)
- [Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory](https://mlsanity.com/paper/2305.02437/) (2023)
- [STMTrack: Template-free Visual Tracking with Space-time Memory Networks](https://mlsanity.com/paper/2104.00324/) (2021)
- [Remember Intentions: Retrospective-Memory-based Trajectory Prediction](https://mlsanity.com/paper/2203.11474/) (2022)
- [Hierarchical Memory Matching Network for Video Object Segmentation](https://mlsanity.com/paper/2109.11404/) (2021)
- [Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources](https://mlsanity.com/paper/2112.00061/) (2021)
- [Large Language Models can Learn Rules](https://mlsanity.com/paper/2310.07064/) (2023)
- [When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learning](https://mlsanity.com/paper/2203.16797/) (2022)
- [Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey](https://mlsanity.com/paper/2402.05391/) (2024)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detection](https://mlsanity.com/paper/2104.00902/) (2021)
- [Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generation](https://mlsanity.com/paper/2111.04318/) (2021)
- [Towards General Purpose Vision Systems](https://mlsanity.com/paper/2104.00743/) (2021)
- [SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2111.13495/) (2021)
- [DialogueNeRF: Towards Realistic Avatar Face-to-Face Conversation Video Generation](https://mlsanity.com/paper/2203.07931/) (2022)
- [Using natural language prompts for machine translation](https://mlsanity.com/paper/2202.11822/) (2022)
- [Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data](https://mlsanity.com/paper/2205.07557/) (2022)
- [Automated Data Curation for Robust Language Model Fine-Tuning](https://mlsanity.com/paper/2403.12776/) (2024)
- [SMEMO: Social Memory for Trajectory Forecasting](https://mlsanity.com/paper/2203.12446/) (2022)
- [A Survey on User Behavior Modeling in Recommender Systems](https://mlsanity.com/paper/2302.11087/) (2023)
- [MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detection](https://mlsanity.com/paper/2312.02530/) (2023)

## Abstract (arXiv)

Most tasks in natural language processing can be cast into question answering (QA) problems over language input. We introduce the dynamic memory network (DMN), 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 can be trained end-to-end and obtains state-of-the-art results on several types of tasks and datasets: question answering (Facebook's bAbI dataset), text classification for sentiment analysis (Stanford Sentiment Treebank) and sequence modeling for part-of-speech tagging (WSJ-PTB). The training for these different tasks relies exclusively on trained word vector representations and input-question-answer triplets.