实现古诗和对联的自动生成是极具挑战性的任务。该文提出了一种新颖的多任务学习模型用于古诗和对联的自动生成。模型采用编码-解码结构并融入注意力机制,编码部分由两个BiLSTM组成,一个BiLSTM用于关键词输入,另一个BiLSTM用于古诗和对联输入;解码部分由两个LSTM组成,一个LSTM用于古诗的解码输出,另一个LSTM用于对联的解码输出。在中国的传统文学中,古诗和对联具有很多的相似特征,多任务学习模型通过编码器参数共享,解码器参数不共享,让模型底层编码部分兼容古诗和对联特征,解码部分保留各自特征,增强模型泛化能力,表现效果大大优于单任务模型。同时,该文在模型中创新性地引入关键词信息,让生成的古诗及对联表达内容与用户意图一致。最后,该文采用自动评估和人工评估两种方式验证了方法的有效性。
Abstract
This paper proposes a novel multi-task learning model for the automatic generation of classical poetry and couplet, which uses an encoder-decoder structure and the attention mechanism. The encoder consists of two BiLSTMs, one for keyword input, the other for classical poetry and couplet input. The decoder consists of two LSTMs, one for classical poetry output, the other for couplet output. In the multi-task learning model, the encoder parameters are shared and the decoder parameters are not shared. The encoder of model can learn the common features of classical poetry and couplet, the decoder of classical model can learn the unique features of classical poetry and couplet. So, the generalization ability of the model will be enhanced, and the performance will be much better than the single task model. At the same time, this paper innovatively introduces keyword information in the model, so that the generated classical poetry and couplet are consistent with the user's intention. At the end of this paper, automa-tic evaluation and manual evaluation are used to verify the effectiveness of the method.
关键词
LSTM /
多任务学习 /
注意力机制 /
古诗对联生成
{{custom_keyword}} /
Key words
LSTM /
multi-task learning /
attention mechanism /
classical poetry and couplet generation
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Wang Li. A Summary of Rhyming Constraints of Chinese Poems (Shi Ci Ge Lv Gai Yao)[M]. Beijing: Beijing Press,2002.
[2] Naoko Tosa,Hideto Obara,Michihiko Minoh. Hitch haiku: An interactive supporting system for composing haiku poem[C]//Proceedings of Entertainment Computing-ICEC 2008,2008: 209-216.
[3] Xiaofeng Wu,Naoko Tosa,Ryohei Nakatsu. New hitch haiku: An interactive renku poem composition supporting tool applied for sightseeing navigation system[C]//Proceedings of Entertainment Computing-ICEC 2009,2009: 191-196.
[4] Yael Netzer,David Gabay,Yoav Goldberg,et al. Gaiku: Generating haiku with word associations norms[C]//Proceedings of the Workshop on Computational Approaches to Linguistic Creativity,Association for Computational Linguistics,2009: 32-39.
[5] Oliveira H. Automatic generation of poetry: an overview[D]. Universidade de Coimbra,2009.
[6] Oliveira H G. PoeTryMe: a versatile platform for poetry generation[J]. Computational Creativity,Concept Invention,and General Intelligence,2012,1: 21.
[7] 张开旭,孙茂松. 统计与规则相结合的古文对联应对模型[J]. 中文信息学报,2009,23(1): 100-105.
[8] Ruli Manurung,Graeme Ritchie,Henry Thompson. Using genetic algorithms to create meaningful poetic text[J]. Journal of Experimental & Theoretical Artificial Intelligence,24(1): 43-64. 2012
[9] Manurung H. An evolutionary algorithm approach to poetry generation[D]. Edinburgh: University of Edinburgh,2004.
[10] Chengle Zhou,Wei You,Xiaojun Ding. Genetic algorithm and its implementation of automatic generation of chinese songci[J]. Journal of Software,2010,21(3): 427-437.
[11] Rui Yan,Han Jiang,Mirella Lapata,poet: Automatic Chinese poetry composition through a generative summarization framework under constrained optimization[C]//Proceedings of IJCAI,2013.
[12] Jing He,Ming Zhou,Long Jiang. Generating Chinese classical poems with statistical machine translation models[C]//Proceedings of the 26 AAAI Conference on Artificial Intelligence,2012.
[13] Long Jiang,Ming Zhou. Generating Chinese couplets using a statistical mt approach[C]//Proceedings of the 22nd International Conference on Computational Linguistics-Volume 1,Association for Computational Linguistics. 2008: 377-384.
[14] Xingxing Zhang,Mirella Lapata. Chinese poetry generation with recurrent neural networks[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP),2014: 670-680.
[15] Qixin Wang,Tianyi Luo,Dong Wang,et al. Chinese song iambics generation with neural attention-based model [J/OL].CoRR,abs/1604.06274.2016.
[16] Wang Z,He W,Wu H,et al. Chinese poetry generation with planning based neural network[J/OL]. arXiv preprint arXiv: 1610.09889,2016.
[17] Yi X,Li R,Sun M. Generating chinese classical poems with rnn encoder-decoder[M].Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data. Springer,Cham,2017: 211-223.
[18] Yan R,Li C T,Hu X,et al. Chinese couplet generation with neural network structures[C]//Proceedings of Meeting of the Association for Computational Linguistics. 2016.
[19] Erica Greene,Tugba Bodrumlu,Kevin Knight. Automatic analysis of rhythmic poetry with applications to generation and translation[C]//Proceedings of EMNLP.2010.
[20] Simon Colton,Jacob Goodwin,Tony Veale. Full-face poetry generation[C]//Proceedings of ICCC.2012.
[21] Tomas Mikolov. Recurrent neural network based language model[C]//Proceedings of INTERSPEECH,2010.
[22] Yejin Choi Marjan Ghazvininejad,Xing Shi,Kevin Knight. Generating topical poetry[C]//Proceedings of EMNLP,2016.
[23] Sutskever I,Vinyals O,Le Q V. Sequence to sequence learning with neural networks[C]//Proceedings of Advances in neural information processing systems. 2014: 3104-3112.
[24] Rada Mihalcea,Paul Tarau. Textrank: Bringing order into text[C]//Proceedings of EMNLP,2004.
[25] Sergey Brin,Lawrence Page. The anatomy of a large-scale hypertextual web search engine[J]. Computer Networks,1998,30: 107-117.
[26] 黄文明,卫万成,邓珍荣.基于序列到序列神经网络模型的古诗自动生成方法[J/OL].计算机应用研究: 1-7[2018-11-24].http: //kns.cnki.net/kcms/detail/51.1196.TP.20180927.1211.008.html.
[27] Dong D,Wu H,He W,et al. Multi-task learning for multiple language translation[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2015: 1723-1732.
[28] Matthew D Zeiler. Adadelta: An adaptive learning rate method[J/OL]. CoRR,abs/1212.5701. 2012.
[29] Papineni K,Roukos S,Ward T,et al. BLEU: A method for automatic evaluation of machine translation[C]//Proceedings of the 40th Annual Meeting on Association for Computational Linguistics. Association for Computational Linguistics,2002: 311-318.
[30] 蒋锐滢,崔磊,何晶,等. 基于主题模型和统计机器翻译方法的中文格律诗自动生成[J]. 计算机学报,2015,38(12): 2426-2436.
[31] Dzmitry Bahdanau,Kyunghyun Cho,Yoshua Bengio. Neural machine translation by jointly learning to align and translate[J/OL]. arXiv preprint arXiv: 1409.0473. 2014.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
广西高校云计算与复杂系统重点实验室资助项目(yf17106);广西自然科学基金(2018GXNSFAA138132);桂林电子科技大学研究生教育创新计划资助项目(2018YJCX55)
{{custom_fund}}
PDF(4179 KB)
