Page 319 - 《软件学报》2026年第2期

798 软件学报 2026 年第 37 卷第 2 期

10.1145/3539618.3592036]
[47] Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv:1412.6980, 2017.
[48] Paulus R, Xiong CM, Socher R. A deep reinforced model for abstractive summarization. arXiv:1705.04304, 2017.
[49] Lin CY. ROUGE: A package for automatic evaluation of summaries. In: Text Summarization Branches Out. Barcelona: Association for
Computational Linguistics, 2004. 74–81.
[50] Papineni K, Roukos S, Ward T, Zhu WJ. BLEU: A method for automatic evaluation of machine translation. In: Proc. of the 40th Annual
Meeting of the Association for Computational Linguistics. Philadelphia: Association for Computational Linguistics, 2002. 311–318. [doi:
10.3115/1073083.1073135]
[51] Denkowski M, Lavie A. Meteor universal: Language specific translation evaluation for any target language. In: Proc. of the 9th Workshop
on Statistical Machine Translation. Baltimore: Association for Computational Linguistics, 2014. 376–380. [doi: 10.3115/v1/W14-3348]
[52] Lewis M, Liu YH, Goyal N, Ghazvininejad M, Mohamed A, Levy O, Stoyanov V, Zettlemoyer L. BART: Denoising sequence-to-
sequence pre-training for natural language generation, translation, and comprehension. arXiv:1910.13461, 2019.
[53] Touvron H, Lavril T, Izacard G, Martinet X, Lachaux MA, Lacroix T, Rozière B, Goyal N, Hambro E, Azhar F, Rodriguez A, Joulin A,
Grave E, Lample G. LLaMA: Open and efficient foundation language models. arXiv:2302.13971, 2023.
[54] Ouyang L, Wu J, Jiang X, Almeida D, Wainwright CL, Mishkin P, Zhang C, Agarwal S, Slama K, Ray A, Schulman J, Hilton J, Kelton
F, Miller L, Simens M, Askell A, Welinder P, Christiano P, Leike J, Lowe R. Training language models to follow instructions with
human feedback. In: Proc. of the 36th Int’l Conf. on Neural Information Processing Systems. New Orleans: Curran Associates Inc., 2022.
27730–27744.
[55] Wang JF, Yang ZY, Hu XW, Li LJ, Lin K, Gan Z, Liu ZC, Liu C, Wang LJ. GIT: A generative image-to-text Transformer for vision and
language. arXiv:2205.14100, 2022.
[56] Lee K, Joshi M, Turc I, Hu HX, Liu FY, Eisenschlos J, Khandelwal U, Shaw P, Chang MW, Toutanova K. Pix2Struct: Screenshot
parsing as pretraining for visual language understanding. In: Proc. of the 40th Int’l Conf. on Machine Learning. 2023. 18893–18912.
[57] Liu HT, Li CY, Wu QY, Lee YJ. Visual instruction tuning. In: Proc. of the 37th Int’l Conf. on Neural Information Processing Systems.
New Orleans: Curran Associates Inc., 2023. 34892–34916.
[58] Li B, Lv CH, Zhou ZF, Zhou T, Xiao T, Ma AX, Zhu JB. On vision features in multimodal machine translation. arXiv:2203.09173, 2022.
[59] Ling Y, Yu JF, Xia R. Vision-language pre-training for multimodal aspect-based sentiment analysis. arXiv:2204.07955, 2022.
[60] Zhou R, Guo WY, Liu XM, Yu SL, Zhang Y, Yuan XJ. AoM: Detecting aspect-oriented information for multimodal aspect-based
sentiment analysis. arXiv:2306.01004, 2023.

附中文参考文献
[12] 陈洁, 王思雨, 赵姝, 张燕平, 余静莹. 基于多粒度用户偏好的文档级情感分析. 中文信息学报, 2023, 37(7): 122–130. [doi: 10.3969/
j.issn.1003-0077.2023.07.015]
[13] 夏辉丽, 杨立身, 薛峰. 利用自注意力机制的大规模网络文档情感分析. 计算机工程与设计, 2021, 42(9): 2642–2648. [doi: 10.
16208/j.issn1000-7024.2021.09.032]
[14] 李卫疆, 漆芳, 余正涛. 基于多通道特征和自注意力的情感分类方法. 软件学报, 2021, 32(9): 2783–2800. http://www.jos.org.cn/1000-
9825/5992.htm [doi: 10.13328/j.cnki.jos.005992]
[25] 黄璐, 林川杰, 何军, 刘红岩, 杜小勇. 融合主题模型和协同过滤的多样化移动应用推荐. 软件学报, 2017, 28(3): 708–720. http://www.
jos.org.cn/1000-9825/5163.htm [doi: 10.13328/j.cnki.jos.005163]
[26] 陈碧毅, 黄玲, 王昌栋, 景丽萍. 融合显式反馈与隐式反馈的协同过滤推荐算法. 软件学报, 2020, 31(3): 794–805. http://www.jos.org.
cn/1000-9825/5897.htm [doi: 10.13328/j.cnki.jos.005897]

作者简介
强敏杰, 博士生, CCF 学生会员, 主要研究领域为自然语言处理.
王中卿, 博士, 副教授, CCF 专业会员, 主要研究领域为自然语言处理.
李寿山, 博士, 教授, CCF 专业会员, 主要研究领域为自然语言处理.
周国栋, 博士, 教授, 博士生导师, CCF 杰出会员, 主要研究领域为自然语言处理.