Efficient Summarization with Read-Again and Copy Mechanism

TL;DR

This paper introduces a novel encoder-decoder model with a read-again mechanism and a copy mechanism, improving sequence summarization by producing better representations and handling out-of-vocabulary words efficiently.

Contribution

It proposes a simple read-again encoder and a copy mechanism, addressing limitations of existing models in sequence summarization tasks.

Findings

Outperforms state-of-the-art on Gigaword dataset

Achieves faster decoding with small vocabularies

Handles out-of-vocabulary words effectively

Abstract

Encoder-decoder models have been widely used to solve sequence to sequence prediction tasks. However current approaches suffer from two shortcomings. First, the encoders compute a representation of each word taking into account only the history of the words it has read so far, yielding suboptimal representations. Second, current decoders utilize large vocabularies in order to minimize the problem of unknown words, resulting in slow decoding times. In this paper we address both shortcomings. Towards this goal, we first introduce a simple mechanism that first reads the input sequence before committing to a representation of each word. Furthermore, we propose a simple copy mechanism that is able to exploit very small vocabularies and handle out-of-vocabulary words. We demonstrate the effectiveness of our approach on the Gigaword dataset and DUC competition outperforming the state-of-the-art.