# Gated End-to-End Memory Networks

arXiv: https://arxiv.org/abs/1610.04211 · HTML: https://mlsanity.com/paper/1610.04211/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Oct 2016.

## Built on by (most cited first, 6 of 6)

- [StepGame: A New Benchmark for Robust Multi-Hop Spatial Reasoning in Texts](https://mlsanity.com/paper/2204.08292/) (2022)
- [A Cooperative Memory Network for Personalized Task-oriented Dialogue Systems with Incomplete User Profiles](https://mlsanity.com/paper/2102.08322/) (2021)
- [SemanticCAP: Chromatin Accessibility Prediction Enhanced by Features Learning from a Language Model](https://mlsanity.com/paper/2204.02130/) (2022)
- [Point Cloud Completion Guided by Prior Knowledge via Causal Inference](https://mlsanity.com/paper/2305.17770/) (2023)
- [A2P-MANN: Adaptive Attention Inference Hops Pruned Memory-Augmented Neural Networks](https://mlsanity.com/paper/2101.09693/) (2021)
- [Learning Complex Users' Preferences for Recommender Systems](https://mlsanity.com/paper/2107.01529/) (2021)

## Abstract (arXiv)

Machine reading using differentiable reasoning models has recently shown remarkable progress. In this context, End-to-End trainable Memory Networks, MemN2N, have demonstrated promising performance on simple natural language based reasoning tasks such as factual reasoning and basic deduction. However, other tasks, namely multi-fact question-answering, positional reasoning or dialog related tasks, remain challenging particularly due to the necessity of more complex interactions between the memory and controller modules composing this family of models. In this paper, we introduce a novel end-to-end memory access regulation mechanism inspired by the current progress on the connection short-cutting principle in the field of computer vision. Concretely, we develop a Gated End-to-End trainable Memory Network architecture, GMemN2N. From the machine learning perspective, this new capability is learned in an end-to-end fashion without the use of any additional supervision signal which is, as far as our knowledge goes, the first of its kind. Our experiments show significant improvements on the most challenging tasks in the 20 bAbI dataset, without the use of any domain knowledge. Then, we show improvements on the dialog bAbI tasks including the real human-bot conversion-based Dialog State Tracking Challenge (DSTC-2) dataset. On these two datasets, our model sets the new state of the art.