Long Short-Term Memory-Networks for Machine Reading
This work addresses the challenge of handling structured input in sequence processing for natural language tasks, offering a novel architecture that enhances memory capabilities.
The paper tackled the problem of improving sequence-level networks for structured input by proposing a machine reading simulator that extends LSTM with a memory network, enabling adaptive memory usage and shallow reasoning. Experiments on language modeling, sentiment analysis, and natural language inference showed the model matches or outperforms state-of-the-art results.
In this paper we address the question of how to render sequence-level networks better at handling structured input. We propose a machine reading simulator which processes text incrementally from left to right and performs shallow reasoning with memory and attention. The reader extends the Long Short-Term Memory architecture with a memory network in place of a single memory cell. This enables adaptive memory usage during recurrence with neural attention, offering a way to weakly induce relations among tokens. The system is initially designed to process a single sequence but we also demonstrate how to integrate it with an encoder-decoder architecture. Experiments on language modeling, sentiment analysis, and natural language inference show that our model matches or outperforms the state of the art.