AI and poetry创作诗歌对于人来说都很难,对于机器来说就更是难上加难了。虽然机器与人相比,在一些方面有着先天的优势,例如,机器有无穷无尽的词汇库可供选择,机器可以很容易的解决对仗、平仄和押韵等问题。但是,真正的诗歌是有灵魂的,诗歌本质上是在传达诗人的思想。机器自动创作在主题控制方面很弱,很难让整首诗都围绕一个统一的主题来生成。目前文本生成的模型(例如GPT-2)等,已经取得了不错的效果,例如华为已经开发了“乐府”系统等。
national conference on artificial intelligence, (2020)
In this work, inspired by related literature theories, we propose MixPoet2 to address the problem of poor diversity in poetry generation
Cited by2BibtexViews422
0
0
Tim Van de Cruys
ACL, pp.2471-2480, (2020)
We explore how these approaches can be adapted and combined to model the linguistic and literary aspects needed for poetry generation
Cited by0BibtexViews147
0
0
ACL, pp.742-751, (2020)
We propose to tackle a challenging task called rigid formats controlled text generation
Cited by0BibtexViews362
0
0
Liming Deng, Jie Wang, Hangming Liang, Hui Chen, Zhiqiang Xie,Bojin Zhuang, Shaojun Wang, Jing Xiao
national conference on artificial intelligence, (2020)
We present an iterative polishing framework for Chinese poetry generation by imitating the real poem writing process
Cited by0BibtexViews122
0
0
Hu Jinyi,Sun Maosong
LREC, pp.4658-4663, (2020)
We at first define a unified format for formulating all types of training samples by integrating more detailed form information, present a simple form-stressed weighting method in GPT2 to strengthen the control to the form of CI
Cited by0BibtexViews184
0
0
ACL (3), pp.25-30, (2019)
We demonstrate Jiuge, a human-machine collaborative Chinese classical poetry generation system
Cited by7BibtexViews141DOI
0
0
IJCAI, pp.4925-4931, (2019)
We introduce a fine-grained sentimental poetry corpus and propose a sentiment-controllable poetry generation model 3
Cited by6BibtexViews239DOI
0
0
Zhichao Yang, Pengshan Cai,Yansong Feng, Fei Li, Weijiang Feng, ElenaSuet-Ying Chiu,Hong Yu
Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Emp..., (2019): 6155-6164
We proposed a novel task of generating classical Chinese poems from vernacular paragraphs
Cited by3BibtexViews212DOI
0
0
Zhiqiang Liu,Zuohui Fu, Jie Cao, Gerard de Melo, Yik-Cheung Tam,Cheng Niu, Jie Zhou
ACL (1), pp.1992-2001, (2019)
We propose a rhetorically controlled encoder-decoder for modern Chinese poetry generation
Cited by3BibtexViews148DOI
0
0
Mika Hämäläinen, Khalid Alnajjar
EMNLP/IJCNLP (1), pp.5998-6003, (2019)
We present a novel approach based on a genetic algorithm for creating poetry in Finnish from the stand point of computational creativity
Cited by0BibtexViews115DOI
0
0
MM '18: ACM Multimedia Conference Seoul Republic of Korea October, 2018, (2018): 783-791
Automatic generation of natural language from images has attracted extensive attention. In this paper, we take one step further to investigate generation of poetic language (with multiple lines) to an image for automatic poetry creation. This task involves multiple challenges, in...
Cited by24BibtexViews180DOI
0
0
EMNLP, pp.3143-3153, (2018)
We address two substantial problems in automatic poetry generation: lack of diversity, and loss-evaluation mismatch, which are caused by maximum likelihood estimation-based neural models
Cited by23BibtexViews155
0
0
EMNLP, pp.3960-3969, (2018)
As the first attempt on unsupervised style disentanglement, we find Chinese poetry generation is an ideal choice for evaluation because we can better focus on stylistic generation rather than dealing with genre requirements
Cited by19BibtexViews212
0
0
IJCAI, (2018): 4553-4559
As an exquisite and concise literary form, poetry is a gem of human culture. Automatic poetry generation is an essential step towards computer creativity. In recent years, several neural models have been designed for this task. However, among lines of a whole poem, the coherence ...
Cited by19BibtexViews100
0
0
EMNLP, pp.3890-3900, (2018)
We proposed an effective approach that integrates conditional variational autoencoders and adversarial training for classical Chinese poem generation
Cited by17BibtexViews162
0
0
THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTI..., (2018): 5618-5625
Semantic keywords are extracted as the skeleton of a poem, where a topic memory network is proposed that can take as many keywords as possible and dynamically select the most relevant ones to use during poem generation
Cited by15BibtexViews138
0
0
Xiaopeng Yang, Xiaowen Lin, Shunda Suo,Ming Li
IJCAI, pp.4539-4545, (2018)
We have proposed a conditional variational autoencoder with a hybrid decoder to mine the implicit topic information contained within poems lines
Cited by11BibtexViews122
0
0
CoNLL, (2018): 241-250
We address the problem of the context coherence in poetry generation
Cited by8BibtexViews132
0
0
IJCNN, (2018)
Our experiments demonstrate that the proposed methods of title generation and poetry generation both outperform the strong baselines
Cited by5BibtexViews220DOI
0
0
CCL, (2017): 211-223
We take the generation of poem lines as a sequence-to-sequence learning problem, and build a novel system to generate quatrains based on RNN Encoder-Decoder
Cited by76BibtexViews191DOI
0
0
小科