Ordered Memory

TL;DR

The paper introduces Ordered Memory, a novel neural architecture with an attention mechanism and recursive cell, improving logical inference, interpretability, and sentiment analysis performance.

Contribution

It proposes the Ordered Memory architecture, combining a new attention-based mechanism and Gated Recursive Cell for enhanced memory control and interpretability.

Findings

Strong performance on logical inference and ListOps tasks

Induced tree structures align with ground truth

Competitive results on Stanford SentimentTreebank

Abstract

Stack-augmented recurrent neural networks (RNNs) have been of interest to the deep learning community for some time. However, the difficulty of training memory models remains a problem obstructing the widespread use of such models. In this paper, we propose the Ordered Memory architecture. Inspired by Ordered Neurons (Shen et al., 2018), we introduce a new attention-based mechanism and use its cumulative probability to control the writing and erasing operation of the memory. We also introduce a new Gated Recursive Cell to compose lower-level representations into higher-level representation. We demonstrate that our model achieves strong performance on the logical inference task (Bowman et al., 2015)and the ListOps (Nangia and Bowman, 2018) task. We can also interpret the model to retrieve the induced tree structure, and find that these induced structures align with the ground truth. Finally, we evaluate our model on the Stanford SentimentTreebank tasks (Socher et al., 2013), and find that it performs comparatively with the state-of-the-art methods in the literature.