Incorporating Copying Mechanism in Sequence-to-Sequence Learning

TL;DR

This paper introduces CopyNet, a neural network model that effectively integrates copying mechanisms into sequence-to-sequence learning, improving performance on tasks like text summarization by selectively replicating input segments.

Contribution

The paper proposes CopyNet, a novel encoder-decoder model that combines traditional word generation with a copying mechanism for better sequence replication.

Findings

CopyNet outperforms standard RNN models on text summarization.

CopyNet effectively handles copying of input segments in synthetic and real datasets.

Empirical results show significant improvements in copying accuracy.

Abstract

We address an important problem in sequence-to-sequence (Seq2Seq) learning referred to as copying, in which certain segments in the input sequence are selectively replicated in the output sequence. A similar phenomenon is observable in human language communication. For example, humans tend to repeat entity names or even long phrases in conversation. The challenge with regard to copying in Seq2Seq is that new machinery is needed to decide when to perform the operation. In this paper, we incorporate copying into neural network-based Seq2Seq learning and propose a new model called CopyNet with encoder-decoder structure. CopyNet can nicely integrate the regular way of word generation in the decoder with the new copying mechanism which can choose sub-sequences in the input sequence and put them at proper places in the output sequence. Our empirical study on both synthetic data sets and real world data sets demonstrates the efficacy of CopyNet. For example, CopyNet can outperform regular RNN-based model with remarkable margins on text summarization tasks.