Recurrently Controlled Recurrent Networks

Abstract

Recurrent neural networks (RNNs) such as long short-term memory and gated recurrent units are pivotal building blocks across a broad spectrum of sequence modeling problems. This paper proposes a recurrently controlled recurrent network (RCRN) for expressive and powerful sequence encoding. More concretely, the key idea behind our approach is to learn the recurrent gating functions using recurrent networks. Our architecture is split into two components - a controller cell and a listener cell whereby the recurrent controller actively influences the compositionality of the listener cell. We conduct extensive experiments on a myriad of tasks in the NLP domain such as sentiment analysis (SST, IMDb, Amazon reviews, etc.), question classification (TREC), entailment classification (SNLI, SciTail), answer selection (WikiQA, TrecQA) and reading comprehension (NarrativeQA). Across all 26 datasets, our results demonstrate that RCRN not only consistently outperforms BiLSTMs but also stacked BiLSTMs, suggesting that our controller architecture might be a suitable replacement for the widely adopted stacked architecture.

arXiv commentNIPS 2018

Cited by in corpus (7)

• Deep Learning-based Sentiment Classification: A Comparative Survey
• CodeGRU: Context-aware Deep Learning with Gated Recurrent Unit for Source Code Modeling
• Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives
• A Dynamically Controlled Recurrent Neural Network for Modeling Dynamical Systems
• Multi-Scale Quasi-RNN for Next Item Recommendation
• Depth-Adaptive Graph Recurrent Network for Text Classification
• Modeling Multi-Action Policy for Task-Oriented Dialogues