Flexible and creative Chinese poetry generation using neural memory

Jiyuan Zhang; Yang Feng; Dong Wang; Yang Wang; Andrew Abel; Shiyue Zhang; Andi Zhang

doi:10.18653/v1/P17-1125

Flexible and creative Chinese poetry generation using neural memory

Jiyuan Zhang, Yang Feng, Dong Wang^*, Yang Wang, Andrew Abel, Shiyue Zhang, Andi Zhang

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

73 Citations (Scopus)

18 Downloads (Pure)

Abstract

It has been shown that Chinese poems can be successfully generated by sequence-to-sequence neural models, particularly with the attention mechanism. A potential problem of this approach, however, is that neural models can only learn abstract rules, while poem generation is a highly creative process that involves not only rules but also innovations for which pure statistical models are not appropriate in principle. This work proposes a memory-augmented neural model for Chinese poem generation, where the neural model and the augmented memory work together to balance the requirements of linguistic accordance and aesthetic innovation, leading to innovative generations that are still rule-compliant. In addition, it is found that the memory mechanism provides interesting flexibility that can be used to generate poems with different styles.

Original language	English
Title of host publication	ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Pages	1364-1373
Number of pages	10
Volume	1
ISBN (Electronic)	9781945626753
DOIs	https://doi.org/10.18653/v1/P17-1125
Publication status	Published - 30 Jul 2017
Event	55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - Vancouver, Canada Duration: 30 Jul 2017 → 4 Aug 2017

Publication series

Name	ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Volume	1

Conference

Conference	55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
Country/Territory	Canada
City	Vancouver
Period	30/07/17 → 4/08/17

Funding

This paper was supported by the National Natural Science Foundation of China (NSFC) under the project NO.61371136, NO.61633013, NO.61472428.

Keywords

neural memory
Chinese poems
neural models
augmented memory

Access to Document

10.18653/v1/P17-1125

Zhang-etal-ACL2017-Flexible-creative-Chinese-poetry-generation-using-neural-memoryFinal published version, 725 KBLicence: CC BY 4.0

Cite this

Zhang, J., Feng, Y., Wang, D., Wang, Y., Abel, A., Zhang, S., & Zhang, A. (2017). Flexible and creative Chinese poetry generation using neural memory. In ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) (Vol. 1, pp. 1364-1373). (ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); Vol. 1). https://doi.org/10.18653/v1/P17-1125

Zhang, Jiyuan ; Feng, Yang ; Wang, Dong et al. / Flexible and creative Chinese poetry generation using neural memory. ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Vol. 1 2017. pp. 1364-1373 (ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)).

@inproceedings{7786a23805644d86a95ce52a03f2e768,

title = "Flexible and creative Chinese poetry generation using neural memory",

abstract = "It has been shown that Chinese poems can be successfully generated by sequence-to-sequence neural models, particularly with the attention mechanism. A potential problem of this approach, however, is that neural models can only learn abstract rules, while poem generation is a highly creative process that involves not only rules but also innovations for which pure statistical models are not appropriate in principle. This work proposes a memory-augmented neural model for Chinese poem generation, where the neural model and the augmented memory work together to balance the requirements of linguistic accordance and aesthetic innovation, leading to innovative generations that are still rule-compliant. In addition, it is found that the memory mechanism provides interesting flexibility that can be used to generate poems with different styles.",

keywords = "neural memory, Chinese poems, neural models, augmented memory",

author = "Jiyuan Zhang and Yang Feng and Dong Wang and Yang Wang and Andrew Abel and Shiyue Zhang and Andi Zhang",

note = "Funding Information: This paper was supported by the National Natural Science Foundation of China (NSFC) under the project NO.61371136, NO.61633013, NO.61472428. Publisher Copyright: {\textcopyright} 2017 Association for Computational Linguistics. Jiyuan Zhang, Yang Feng, Dong Wang, Yang Wang, Andrew Abel, Shiyue Zhang, and Andi Zhang. 2017. Flexible and Creative Chinese Poetry Generation Using Neural Memory. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1364–1373, Vancouver, Canada. Association for Computational Linguistics. DOI: 10.18653/v1/P17-1125; 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 ; Conference date: 30-07-2017 Through 04-08-2017",

year = "2017",

month = jul,

day = "30",

doi = "10.18653/v1/P17-1125",

language = "English",

volume = "1",

series = "ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)",

pages = "1364--1373",

booktitle = "ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)",

}

Zhang, J, Feng, Y, Wang, D, Wang, Y, Abel, A, Zhang, S & Zhang, A 2017, Flexible and creative Chinese poetry generation using neural memory. in ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). vol. 1, ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers), vol. 1, pp. 1364-1373, 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, 30/07/17. https://doi.org/10.18653/v1/P17-1125

Flexible and creative Chinese poetry generation using neural memory. / Zhang, Jiyuan; Feng, Yang; Wang, Dong et al.
ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Vol. 1 2017. p. 1364-1373 (ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

TY - GEN

T1 - Flexible and creative Chinese poetry generation using neural memory

AU - Zhang, Jiyuan

AU - Feng, Yang

AU - Wang, Dong

AU - Wang, Yang

AU - Abel, Andrew

AU - Zhang, Shiyue

AU - Zhang, Andi

N1 - Funding Information: This paper was supported by the National Natural Science Foundation of China (NSFC) under the project NO.61371136, NO.61633013, NO.61472428. Publisher Copyright: © 2017 Association for Computational Linguistics. Jiyuan Zhang, Yang Feng, Dong Wang, Yang Wang, Andrew Abel, Shiyue Zhang, and Andi Zhang. 2017. Flexible and Creative Chinese Poetry Generation Using Neural Memory. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1364–1373, Vancouver, Canada. Association for Computational Linguistics. DOI: 10.18653/v1/P17-1125

PY - 2017/7/30

Y1 - 2017/7/30

N2 - It has been shown that Chinese poems can be successfully generated by sequence-to-sequence neural models, particularly with the attention mechanism. A potential problem of this approach, however, is that neural models can only learn abstract rules, while poem generation is a highly creative process that involves not only rules but also innovations for which pure statistical models are not appropriate in principle. This work proposes a memory-augmented neural model for Chinese poem generation, where the neural model and the augmented memory work together to balance the requirements of linguistic accordance and aesthetic innovation, leading to innovative generations that are still rule-compliant. In addition, it is found that the memory mechanism provides interesting flexibility that can be used to generate poems with different styles.

AB - It has been shown that Chinese poems can be successfully generated by sequence-to-sequence neural models, particularly with the attention mechanism. A potential problem of this approach, however, is that neural models can only learn abstract rules, while poem generation is a highly creative process that involves not only rules but also innovations for which pure statistical models are not appropriate in principle. This work proposes a memory-augmented neural model for Chinese poem generation, where the neural model and the augmented memory work together to balance the requirements of linguistic accordance and aesthetic innovation, leading to innovative generations that are still rule-compliant. In addition, it is found that the memory mechanism provides interesting flexibility that can be used to generate poems with different styles.

KW - neural memory

KW - Chinese poems

KW - neural models

KW - augmented memory

UR - https://www.scopus.com/pages/publications/85040904362

U2 - 10.18653/v1/P17-1125

DO - 10.18653/v1/P17-1125

M3 - Conference contribution book

AN - SCOPUS:85040904362

VL - 1

T3 - ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)

SP - 1364

EP - 1373

BT - ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)

T2 - 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017

Y2 - 30 July 2017 through 4 August 2017

ER -

Zhang J, Feng Y, Wang D, Wang Y, Abel A, Zhang S et al. Flexible and creative Chinese poetry generation using neural memory. In ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Vol. 1. 2017. p. 1364-1373. (ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)). doi: 10.18653/v1/P17-1125

Flexible and creative Chinese poetry generation using neural memory

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this