|
|
A Review Summary Generation Model with Emotion-Topic Dual-Channel Information |
Li Honglian1,Chen Haotian1,Zhang Le2(),Lv Xueqiang2,Tian Chi2 |
1School of Information & Communication Engineering, Beijing Information Science & Technology University, Beijing 100101, China 2Beijing Key Laboratory of Internet Culture and Digital Dissemination Research, Beijing Information Science & Technology University, Beijing 100101, China |
|
|
Abstract [Objective] This paper aims to solve the problem that traditional automatic summarization technology cannot deeply integrate emotion and topic information synthetically, and cannot solve the lexical deficiency, a review summary generation model integrating emotion and topic information is proposed. [Methods] TextRank is used to dynamically extract the comment topic sentence, and PyABSA model is used to extract the aspect word-emotion word sequence in the topic sentence to concatenate the topic sentence to obtain the final topic information. The emotion sentence is obtained by constructing the emotion word set and Bi-LSTM emotion word extraction model integrating the topic, and the comment text and emotion sentence are concatenated to form dual-channel information with the topic sentence. The attention mechanism is used to obtain topic attention and emotion attention, respectively, and the superposition of them is deeply fused to obtain fusion attention. The single-channel attention of the pointer generation network is replaced, and the final comment summary is generated by the pointer network. [Results] Compared with the comparative experiment Topic+PNG, the proposed pointer generation network with dual-channel information improves the ROUGE-1, ROUGE-2 and ROUGE-L values by 2.87%, 6.14% and 2.64%, respectively. The ablation experiment showed that ROUGE-1, ROUGE-2 and ROUGE-L value of integrating dual-channel information were 4.49%, 3.66% and 4.16% higher than single-channel information. [Limitations] Because fine-grained attribute words may appear in comments, the integration of fine-grained attributes is not considered. [Conclusions] The model can effectively integrate the topic information and emotion information of the comments, improve the quality of the two-channel information fusion, and outperform the comparison model in the summary generation results. The generated summary can contain more emotion and topic information.
|
Received: 02 May 2023
Published: 08 January 2024
|
|
Fund:National Natural Science Foundation of China(62171043);Key Project of the National Language Commission of China(ZDI145-10);Scientific Research Project of the Beijing Municipal Education Commission(KM202311232001) |
Corresponding Authors:
Zhang Le,ORCID:0000-0002-9620-511X,E-mail:zhangle@bistu.edu.cn。
|
[1] |
Li H S, Li Y. Target Damage Distribution Probability Calculation Arithmetic Based on Space Tangential Differential Unit Area[J]. IEEE Sensors Journal, 2015, 15(4): 2274-2279.
|
[2] |
Chakraborty U. The Impact of Source Credible Online Reviews on Purchase Intension: The Mediating Roles of Brand Equity Dimensions[J]. Journal of Research in Interactive Marketing, 2019, 13(2): 142-161.
doi: 10.1108/JRIM-06-2018-0080
|
[3] |
明拓思宇, 陈鸿昶. 文本摘要研究进展与趋势[J]. 网络与信息安全学报, 2018, 4(6): 1-10.
|
[3] |
(Ming Tuosiyu, Chen Hongchang. Research Progress and Trend of Text Summarization[J]. Chinese Journal of Network and Information Security, 2018, 4(6): 1-10.)
|
[4] |
张云纯, 张琨, 徐济铭, 等. 基于图模型的多文档摘要生成算法[J]. 计算机工程与应用, 2020, 56(16): 124-131.
doi: 10.3778/j.issn.1002-8331.1905-0456
|
[4] |
(Zhang Yunchun, Zhang Kun, Xu Jiming, et al. Multi-document Summary Generation Algorithm Based on Graph Model[J]. Computer Engineering and Applications, 2020, 56(16): 124-131.)
doi: 10.3778/j.issn.1002-8331.1905-0456
|
[5] |
Huang C L, Jiang W J, Wu J, et al. Personalized Review Recommendation Based on Users’ Aspect Sentiment[J]. ACM Transactions on Internet Technology, 2020, 20(4): 1-26.
|
[6] |
Mihalcea R, Tarau P. TextRank: Bringing Order into Texts[C]// Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing. 2004: 404-411.
|
[7] |
Gambhir M, Gupta V. Recent Automatic Text Summarization Techniques: A Survey[J]. Artificial Intelligence Review, 2017, 47(1): 1-66.
|
[8] |
谷莹, 李贺, 祝琳琳. 融合主题聚类和语义图模型的产品评论自动摘要方法研究[J]. 图书情报工作, 2022, 66(13): 118-126.
doi: 10.13266/j.issn.0252-3116.2022.13.011
|
[8] |
(Gu Ying, Li He, Zhu Linlin. Research on Automatic Summarization Method of Product Reviews Based on Topic Clustering and Semantic Graph Model[J]. Library and Information Service, 2022, 66(13): 118-126.)
doi: 10.13266/j.issn.0252-3116.2022.13.011
|
[9] |
Rush A M, Chopra S, Weston J. A Neural Attention Model for Abstracti Sentence Summarization[C]// Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 2015: 379-389.
|
[10] |
See A, Liu P J, Manning C D. Get to the Point: Summarization with Pointer-Generator Networks[C]// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1:Long Papers). 2017: 1073-1083.
|
[11] |
郭继峰, 费禹潇, 孙文博, 等. 一种融合主题的PGN-GAN文本摘要模型[J]. 小型微型计算机系统, 2023, 44(1): 199-203.
|
[11] |
(Guo Jifeng, Fei Yuxiao, Sun Wenbo, et al. Text Summarization Model Based on PGN-GAN with Topic[J]. Journal of Chinese Computer Systems, 2023, 44(1): 199-203.)
|
[12] |
Xie N T, Li S J, Ren H L, et al. Abstractive Summarization Improved by WordNet-Based Extractive Sentences[C]// Proceedings of CCF International Conference on Natural Language Processing and Chinese Computing. 2018: 404-415.
|
[13] |
沈彬, 严馨, 周丽华, 等. 基于ERNIE和双重注意力机制的微博情感分析[J]. 云南大学学报(自然科学版), 2022, 44(3): 480-489.
|
[13] |
(Shen Bin, Yan Xin, Zhou Lihua, et al. Microblog Sentiment Analysis Based on ERNIE and Dual Attention Mechanism[J]. Journal of Yunnan University (Natural Sciences Edition), 2022, 44(3): 480-489.)
|
[14] |
高玮军, 朱婧, 赵华洋, 等. 基于TRF-IM模型的个性化酒店评论摘要生成[J]. 计算机工程与应用, 2023, 59(2): 135-142.
doi: 10.3778/j.issn.1002-8331.2107-0144
|
[14] |
(Gao Weijun, Zhu Jing, Zhao Huayang, et al. Personalized Product Review Summary Generation Based on TRF-IM Model[J]. Computer Engineering and Applications, 2023, 59(2): 135-142.)
doi: 10.3778/j.issn.1002-8331.2107-0144
|
[15] |
Xu H Y, Liu H T, Jiao P F, et al. Transformer Reasoning Network for Personalized Review Summarization[C]// Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2021: 1452-1461.
|
[16] |
林莉媛, 王中卿, 李寿山, 等. 基于PageRank的中文多文档文本情感摘要[J]. 中文信息学报, 2014, 28(2): 85-90.
|
[16] |
(Lin Liyuan, Wang Zhongqing, Li Shoushan, et al. Chinese Multi-Document Opinion Summarization via PageRank[J]. Journal of Chinese Information Processing, 2014, 28(2): 85-90.)
|
[17] |
Yang H, Zhang C, Li K. PyABSA: A Modularized Framework for Reproducible Aspect-Based Sentiment Analysis[C]// Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. 2022: 5117-5122.
|
[18] |
Che W X, Feng Y L, Qin L B, et al. N-LTP: An Open-Source Neural Language Technology Platform for Chinese[C]// Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing:System Demonstrations. 2021: 42-49.
|
[19] |
章成志, 童甜甜, 周清清. 基于细粒度评论挖掘的书评自动摘要研究[J]. 情报学报, 2021, 40(2): 163-172.
|
[19] |
(Zhang Chengzhi, Tong Tiantian, Zhou Qingqing. Automatic Summarization of Book Reviews Based on Fine-Grained Review Mining[J]. Journal of the China Society for Scientific and Technical Information, 2021, 40(2): 163-172.)
|
[20] |
Hochreiter S, Schmidhuber J. Long Short-Term Memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
doi: 10.1162/neco.1997.9.8.1735
pmid: 9377276
|
[21] |
Bahdanau D, Cho K, Bengio Y. Neural Machine Translation by Jointly Learning to Align and Translate[OL]. arXiv Preprint, arXiv: 1409. 0473.
|
[22] |
Mikolov T, Chen K, Corrado G S, et al. Efficient Estimation of Word Representations in Vector Space[OL]. arXiv Preprint, arXiv: 1301. 3781.
|
[23] |
李岱峰, 林凯欣, 李栩婷. 基于提示学习与T5 PEGASUS的图书宣传自动摘要生成器[J]. 数据分析与知识发现, 2023, 7(3): 121-130.
|
[23] |
(Li Daifeng, Lin Kaixin, Li Xuting. Automated Book Summary Generator Based on Prompt Learning and T5 PEGASUS[J]. Data Analysis and Knowledge Discovery, 2023, 7(3): 121-130.)
|
[24] |
张宜飞, 张迎, 王中卿, 等. 基于上下文信息的产品评论摘要Bi-LSTM模型[J]. 计算机应用与软件, 2021, 38(6): 113-119.
|
[24] |
(Zhang Yifei, Zhang Ying, Wang Zhongqing, et al. Product Review Summarization Bi-LSTM Model Based on Context Information[J]. Computer Applications and Software, 2021, 38(6): 113-119.)
|
[25] |
Ng J P, Abrecht V. Better Summarization Evaluation with Word Embeddings for ROUGE[C]// Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Stroudsburg. 2015: 1925-1930.
|
[26] |
Lin C Y. Rouge: A Package for Automatic Evaluation of Summaries[C]// Proceedings of the Workshop on Text Summarization Branches Out (WAS 2004). 2004: 74-81.
|
[27] |
李越, 毛存礼, 余正涛, 等. 融合主题及上下文特征的汉缅双语词汇抽取方法[J]. 小型微型计算机系统, 2021, 42(1): 91-95.
|
[27] |
(Li Yue, Mao Cunli, Yu Zhengtao, et al. Method of Chinese Burmese Bilingual Vocabulary Extraction Based on Subject and Context Features[J]. Journal of Chinese Computer Systems, 2021, 42(1): 91-95.)
|
[28] |
Liu Y. Fine-Tune BERT for Extractive Summarization[OL]. arXiv Preprint, arXiv:1903.10318.
|
[29] |
Vintals O, Fortunato M, Jaitly N. Pointer Networks[C]// Proceedings of the 28th International Conference on Neural Information Processing Systems-Volume 2. 2015: 2692-2700.
|
[30] |
Deaton J, Jacobs A, Kenealy K, et al. Transformers and Pointer-Generator Networks for Abstractive Summarization[OL]. 2019. [2023-04-01]. https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1204/reports/custom/15784595.pdf.
|
[31] |
李健智, 王红玲, 王中卿. 基于图卷积网络的专利摘要自动生成研究[J]. 计算机科学, 2022, 49(6A): 172-177.
doi: 10.11896/jsjkx.210400117
|
[31] |
(Li Jianzhi, Wang Hongling, Wang Zhongqing. Automatic Generation of Patent Summarization Based on Graph Convolution Network[J]. Computer Science, 2022, 49(6A): 172-177.)
doi: 10.11896/jsjkx.210400117
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|