Page 176 - 《软件学报》2025年第5期

2076 软件学报 2025 年第 36 卷第 5 期

encoder. In: Proc. of the 2020 Conf. on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational
Linguistics, 2020. 3762–3767. [doi: 10.18653/v1/2020.emnlp-main.307]
[3] Ye J, Xiang L, Zong CQ. Aspect-level sentiment classification combining aspect modeling and curriculum learning. Ruan Jian Xue
Bao/Journal of Software, 2024, 35(9): 4377–4389 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6963.htm [doi: 10.
13328/j.cnki.jos.006963]
[4] Zhao YY, Lu X, Zhao WX, Tian YJ, Qin B. Survey on emotional dialogue techniques. Ruan Jian Xue Bao/Journal of Software, 2024,
35(3): 1377–1402 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6807.htm [doi: 10.13328/j.cnki.jos.006807]
[5] Liang MY, Li DY, Wang SG, Liao J, Zheng JX, Chen Q. Senti-PG-MMR: Research on generation method of sentimental summary of
multi-document travel notes. Journal of Chinese Information Processing, 2022, 36(3): 128–135 (in Chinese with English abstract). [doi:
10.3969/j.issn.1003-0077.2022.03.015]
[6] Xiong SF, Wang KY, Ji DH, Wang BK. A short text sentiment-topic model for product reviews. Neurocomputing, 2018, 297: 94–102.
[doi: 10.1016/j.neucom.2018.02.034]
[7] Catal C, Nangir M. A sentiment classification model based on multiple classifiers. Applied Soft Computing, 2017, 50: 135–141. [doi: 10.
1016/j.asoc.2016.11.022]
[8] Yang M, Yin WP, Qu Q, Tu WT, Shen Y, Chen XJ. Neural attentive network for cross-domain aspect-level sentiment classification.
IEEE Trans. on Affective Computing, 2021, 12(3): 761–775. [doi: 10.1109/TAFFC.2019.2897093]
[9] Chen JJ, Hou HX, Gao J, Ji YT, Bai TG. RGCN: Recurrent graph convolutional networks for target-dependent sentiment analysis. In:
Proc. of the 12th Int’l Conf. on Knowledge Science, Engineering and Management. Athens: Springer, 2019. 667–675. [doi: 10.1007/978-
3-030-29551-6_59]
[10] Zhao CJ, Wang SG, Li DY. Research progress on cross-domain text sentiment classification. Ruan Jian Xue Bao/Journal of Software,
2020, 31(6): 1723–1746 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6029.htm [doi: 10.13328/j.cnki.jos.006029]
[11] Kingma DP, Welling M. Auto-encoding variational Bayes. arXiv:1312.6114, 2014.
[12] Wu CH, Wu FZ, Wu SX, Yuan ZG, Liu JX, Huang YF. Semi-supervised dimensional sentiment analysis with variational autoencoder.
Knowledge-based Systems, 2019, 165: 30–39. [doi: 10.1016/j.knosys.2018.11.018]
[13] Fu XH, Wei YZ, Xu F, Wang T, Lu Y, Li JQ, Huang JZ. Semi-supervised aspect-level sentiment classification model based on variational
autoencoder. Knowledge-based Systems, 2019, 171: 81–92. [doi: 10.1016/j.knosys.2019.02.008]
[14] Wang YY, Meng XJ, Liu XM. Differentially private recurrent variational autoencoder for text privacy preservation. Mobile Networks and
Applications, 2023, 28: 1565–1580. [doi: 10.1007/s11036-023-02096-9]
[15] Kong X, Li BH, Neubig G, Hovy E, Yang YM. An adversarial approach to high-quality, sentiment-controlled neural dialogue generation.
arXiv:1901.07129, 2019.
[16] Liang XW, Du JC, Niu TY, Zhou LJ, Xu RF. Knowledge interpolated conditional variational auto-encoder for knowledge grounded
dialogues. Applied Sciences, 2023, 13(15): 8707. [doi: 10.3390/APP13158707]
[17] Yang Z, Chen ZH, Cai TC, Wang YF, Liao XW. A survey of deep learning based emotional dialogue response. Chinese Journal of
Computers, 2023, 46(12): 2489–2519 (in Chinese with English abstract). [doi: 10.11897/SP.J.1016.2023.02489]
[18] Hoang T, Le H, Quan T. Towards autoencoding variational inference for aspect-based opinion summary. Applied Artificial Intelligence,
2019, 33(9): 796–816. [doi: 10.1080/08839514.2019.1630148]
[19] Xiong Y, Yan MH, Hu X, Ren CH, Tian H. An unsupervised opinion summarization model fused joint attention and dictionary learning.
The Journal of Supercomputing, 2023, 79(16): 17759–17783. [doi: 10.1007/s11227-023-05316-x]
[20] Zhao SJ, Ren HY, Yuan A, Song JM, Goodman N, Ermon S. Bias and generalization in deep generative models: An empirical study. In:
Proc. of the 32nd Int’l Conf. on Neural Information Processing Systems. Montréal: Curran Associates Inc., 2018. 10815–10824.
[21] Kingma DP, Salimans T, Jozefowicz R, Chen X, Sutskever T, Welling M. Improved variational inference with inverse autoregressive
flow. In: Proc. of the 30th Int’l Conf. on Neural Information Processing Systems. Barcelona: Curran Associates Inc., 2016. 4743–4751.
[22] Sønderby CK, Raiko T, Maaløe L, Sønderby SK, Winther O. How to train deep variational autoencoders and probabilistic ladder
networks. arXiv:1602.02282, 2016.
[23] Pu YC, Gan Z, Henao R, Yuan X, Li CY, Stevens A, Carin L. Variational autoencoder for deep learning of images, labels and captions.
In: Proc. of the 30th Int’l Conf. on Neural Information Processing Systems. Barcelona: Curran Associates Inc., 2016. 2360–2368.
[24] Bai RN, Huang RZ, Qin YB, Chen YP, Lin C. HVAE: A deep generative model via hierarchical variational auto-encoder for multi-view
document modeling. Information Sciences, 2023, 623: 40–55. [doi: 10.1016/j.ins.2022.10.052]
[25] Wen YM, Liu S, Miao YQ, Yi XH, Liu CJ. Survey on semi-supervised classification of data streams with concept drifts. Ruan Jian Xue
Bao/Journal of Software, 2022, 33(4): 1287–1314 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6476.htm [doi: 10.