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 - http://www.scopus.com/inward/record.url?scp=85040904362&partnerID=8YFLogxK
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 -