考虑评级信息的音乐评论文本自动生成

doi:10.3778/j.issn.1673-9418.1908075

摘要/Abstract

摘要：

近年来在线唱歌平台作为一种新型的娱乐方式吸引了大量用户。在在线唱歌平台上，评论发布的音乐作品是平台用户之间分享和交流的一种方式，对用户发布作品具有激励作用。但是新用户的作品或者新发布的作品往往缺乏评论，对音乐作品自动生成评论可以在一定程度上解决此问题。在在线唱歌平台上的评论文本与音乐作品的表现评级存在一定的关系。因此，研究考虑音乐作品评级信息的评论文本自动生成的方法。为此提出了一种基于生成式对抗网络的深度文本生成模型GradeGAN，包括生成器、文本判别器和等级判别器，利用文本判别器和等级判别器共同指导生成器生成准确的文本，同时使生成的文本与等级信息相符。在真实的数据集上的实验结果表明，与已有相关模型相比，所提模型在生成评论时不仅具有更高的准确性，同时具有较高的多样性。

关键词: 文本自动生成, 生成式对抗网络（GAN）, 强化学习, 深度学习

Abstract:

Online singing platforms as a new type of entertainment attract huge number of users in recent years. On online singing platform, writing comments for published music is a way for users to share their music pieces and communicate with each other, which has an incentive effect on users to publish music. However, there is usually no comment for a new user's music or a newly released music. Automatic generating comments for these music pieces can solve this problem to some extent. There is a certain relationship between the comments and the performance grade of the music on the online singing platform. Therefore, this paper studies how to automatically generate comments for published music considering its performance level information. To this end, this paper proposes a deep text generation model based on generative adversarial network, called GradeGAN. Major components of this model include generators, text discriminator and grade discriminators, where both text discriminator and grade discriminator are used to guide the generator to generate accurate text and make the generated text match their grades. Experiment conducted on real data sets shows that compared with existing models, the proposed model not only has higher accuracy, but also has high diversity in generating comments.

Key words: automatic text generation, generative adversarial net (GAN), reinforcement learning, deep learning

严丹，何军，刘红岩，杜小勇. 考虑评级信息的音乐评论文本自动生成[J]. 计算机科学与探索, 2020, 14(8): 1389-1396.

YAN Dan, HE Jun, LIU Hongyan, DU Xiaoyong. Considering Grade Information for Music Comment Text Automatic Generation[J]. Journal of Frontiers of Computer Science and Technology, 2020, 14(8): 1389-1396.

参考文献

[1] Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets[C]//Proceedings of the Annual Conference on Neural Information Processing Systems 2014, Montreal, Dec 8-13, 2014. Red Hook: Curran Associates, 2014: 2672-2680.
[2] Yu L T, Zhang W N, Wang J, et al. SeqGAN: sequence gene-rative adversarial nets with policy gradient[C]//Proceedings of the 31st AAAI Conference on Artificial Intelligence, San Francisco, Feb 4-9, 2017. Menlo Park: AAAI, 2017: 2852-2858.
[3] Sutskever I, Vinyals O, Le Q V, et al. Sequence to sequence learning with neural networks[C]//Proceedings of the Annual Conference on Neural Information Processing Systems 2014, Montreal, Dec 8-13, 2014. Red Hook: Curran Associates, 2014: 3104-3112.
[4] Bengio S, Vinyals O, Jaitly N, et al. Scheduled sampling for sequence prediction with recurrent neural networks[C]//Pro-ceedings of the Annual Conference on Neural Information Processing Systems 2015, Montreal, Dec 7-12, 2015. Red Hook: Curran Associates, 2015: 1171-1179.
[5] Denton E L, Chintala S, Szlam A. Deep generative image mo-dels using a Laplacian pyramid of adversarial networks[C]//Proceedings of the Annual Conference on Neural Information Processing Systems 2015, Montreal, Dec 7-12, 2015. Red Hook: Curran Associates, 2015: 1486-1494.
[6] Huszár F. How (not) to train your generative model: scheduled sampling, likelihood, adversary?[J]. arXiv:1511.05101, 2015.
[7] Lin K, Li D Q, He X D, et al. Adversarial ranking for lan-guage generation[C]//Proceedings of the Annual Conference on Neural Information Processing Systems 2017, Long Beach, Dec 4-9, 2017. Red Hook: Curran Associates, 2017: 3155-3165.
[8] Guo J X, Lu S D, Cai H, et al. Long text generation via adve-rsarial training with leaked information[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence, the 30th Innovative Applications of Artificial Intelligence, and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence, New Orleans, Feb 2-7, 2018. Menlo Park: AAAI, 2018: 5141-5148.
[9] Wang K, Wan X J. SentiGAN: generating sentimental texts via mixture adversarial networks[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence, Sto-ckholm, Jul 13-19, 2018: 4446-4452.
[10] Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[11] Cho K, Van Merrienboer B, GülçehreÇ, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Oct 25-29, 2014. Stroudsburg: ACL, 2014: 1724-1734.
[12] Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate[J]. arXiv:1409.0473, 2014.
[13] Bing L D, Li P J, Liao Y, et al. Abstractive multi-document summarization via phrase selection and merging[J]. arXiv:1506.01597, 2015.
[14] Hu B T, Lu Z D, Li H, et al. Convolutional neural network architectures for matching natural language sentences[C]//Proceedings of the Annual Conference on Neural Information Processing Systems 2014, Montreal, Dec 8-13, 2014. Red Hook: Curran Associates, 2014: 2042-2050.
[15] Srivastava N, Hinton G H, Krizhevsky A, et al. Dropout: a simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research, 2014, 15(1): 1929-1958.
[16] Lin C Y. Rouge: a package for automatic evaluation of sum-maries[C]//Proceedings of the Text Summarization Branches Out, Barcelona, Jul 2014. Stroudsburg: ACL, 2004: 74-81.
[17] Stolcke A. SRILM-an extensible language modeling toolkit[C]//Proceedings of the 7th International Conference on Spoken Language Processing, Denver, Sep 16-20, 2002: 1-4.