2016 IncorporatingCopyingMechanismin

• (Gu et al., 2016) ⇒ Jiatao Gu, Zhengdong Lu, Hang Li, and Victor O.K. Li. (2016). “Incorporating Copying Mechanism in Sequence-to-Sequence Learning.” In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). doi:10.18653/v1/P16-1154

Subject Headings: Encoder-Decoder Neural Network; Seq2Seq Neural Network, CopyNet.

Notes

• Article Versions and URLs:
  • ACL Anthology: P16-1154.
  • ArXiv: 1603.06393.
  • DBLP Computer Science Bibliography: GuLLL16.

Cited By

• Google Scholar: ~ 512 Citations.
• Semantic Scholar: ~ 531 Citations.

Quotes

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.

References

;

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2016 IncorporatingCopyingMechanismin	Hang Li Zhengdong Lu Jiatao Gu Victor O.K. Li			Incorporating Copying Mechanism in Sequence-to-Sequence Learning				10.18653/v1/P16-1154		2016