Skip to main content

Advertisement

Log in

Cross-domain aspect/sentiment-aware abstractive review summarization by combining topic modeling and deep reinforcement learning

  • Multi-Source Data Understanding (MSDU)
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Review text has been widely studied in traditional tasks such as sentiment analysis and aspect extraction. However, to date, no work is toward the end-to-end abstractive review summarization that is essential for business organizations and individual consumers to make informed decisions. This study takes the lead to study the aspect/sentiment-aware abstractive review summarization in domain adaptation scenario. Our novel model Abstractive review Summarization with Topic modeling and Reinforcement deep learning (ASTR) leverages the benefits of the supervised deep neural networks, reinforcement learning, and unsupervised probabilistic generative model to strengthen the aspect/sentiment-aware review representation learning. ASTR is a multi-task learning system, which simultaneously optimizes two coupled objectives: domain classification (auxiliary task) and abstractive review summarization (primary task), in which a document modeling module is shared across tasks. The main purpose of our multi-task model is to strengthen the representation learning of documents and safeguard the performance of cross-domain abstractive review summarization. Specifically, ASTR consists of two key components: (1) a domain classifier, working on datasets of both source and target domains to recognize the domain information of texts and transfer knowledge from the source domain to the target domain. In particular, we propose a weakly supervised LDA model to learn the domain-specific aspect and sentiment lexicon representations, which are then fed into the neural hidden states of given reviews to form aspect/sentiment-aware review representations; (2) an abstractive review summarizer, sharing the document modeling module with the domain classifier. The learned aspect/lexicon-aware review representations are fed into a pointer-generator network to generate aspect/sentiment-aware abstractive summaries of given reviews by employing a reinforcement learning algorithm. We conduct extensive experiments on real-life Amazon reviews to evaluate the effectiveness of our model. Quantitatively, ASTR achieves better performance than the state-of-the-art summarization methods in terms of ROUGE score and human evaluation in both out-of-domain and in-domain setups. Qualitatively, our model can generate better sentiment-aware summarization for reviews with different categories and aspects.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1

Similar content being viewed by others

Notes

  1. We select their RL + ML model which obtains second highest ROUGE score but produces summaries of highest readability.

References

  1. Blei DM, Ng AY, Jordan MI (2003) Latent Dirichlet allocation. J Mach Learn Res 3:993–1022

    MATH  Google Scholar 

  2. Caruana R (1998) Multitask learning. In: Learning to learn. Springer, pp 95–133

  3. Chen Q, Zhu X, Ling Z, Wei S, Jiang H (2016) Distraction-based neural networks for modeling documents. In: Proceedings of the international joint conference on artificial intelligence

  4. Chen T-H, Liao Y-H, Chuang C-Y, Hsu W-T, Fu J, Sun M (2017) Show, adapt and tell: adversarial training of cross-domain image captioner. IEEE Int Conf Comput Vis (ICCV) 2:521–530

    Google Scholar 

  5. Cheng J, Lapata M (2016) Neural summarization by extracting sentences and words. In: Proceedings of the 54th annual meeting of the association for computational linguistics, Berlin, Germany. Association for Computational Linguistics, vol 1: long papers, pp 484–494

  6. Chopra S, Auli M, Rush AM (2016) Abstractive sentence summarization with attentive recurrent neural networks. In: The 15th annual conference of the north American chapter of the association for computational linguistics: human language technologies, pp 93–98

  7. Collobert R, Weston J (2008) A unified architecture for natural language processing: deep neural networks with multitask learning. In: The international conference on machine learning, pp 160–167

  8. Ganesan K, Zhai CX, Han J (2010) Opinosis: a graph-based approach to abstractive summarization of highly redundant opinions. In: The 23rd international conference on computational linguistics. ACL, pp 340–348

  9. Gerani S, Mehdad Y, Carenini G, Ng RT, Nejat B (2014) Abstractive summarization of product reviews using discourse structure. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp 1602–1613

  10. Gu J, Lu Z, Li H, Li VOK (2016) Incorporating copying mechanism in sequence-to-sequence learning. ACL 1:1631–1640

    Google Scholar 

  11. Hochreiter S, Schmidhuber J (1997) Long short-term memory. In: Neural computation, pp 1735–1780

    Google Scholar 

  12. Hu M, Liu B (2006) Opinion extraction and summarization on the web. AAAI 7:1621–1624

    Google Scholar 

  13. Kikuchi Y, Neubig G, Sasano R, Takamura H, Okumura M (2016) Controlling output length in neural encoder-decoders. In: EMNLP, pp 1328–1338

  14. Lavie A, Agarwal A (2007) Meteor: an automatic metric for MT evaluation with high levels of correlation with human judgments. In: Proceedings of the second workshop on statistical machine translation. Association for Computational Linguistics, pp 228–231

  15. Li F, Han C, Huang M, Zhu X, Xia Y-J, Zhang S, Yu H (2010) Structure-aware review mining and summarization. In: Proceedings of the 23rd international conference on computational linguistics. Association for Computational Linguistics, pp 653–661

  16. Lin CY (2004) Rouge: a package for automatic evaluation of summaries. In: ACL workshop on text summarization branches out, vol 8

  17. Lin J, Sun X, Ma S, Su Q (2018) Global encoding for abstractive summarization. In: IJCAI

  18. Liu L, Lu Y, Yang M, Qu Q, Zhu J, Li H (2018) Generative adversarial network for abstractive text summarization. In: Association for the advancement of artificial intelligence

  19. Lu Y, Zhai C (2008) Opinion integration through semi-supervised topic modeling. In: Proceedings of the 17th international conference on World Wide Web. ACM, pp 121–130

  20. Luong MT, Le QV, Sutskever I, Vinyals O, Kaiser L (2016) Multi-task sequence to sequence learning. In: International conference on learning representations

  21. Ly DK, Sugiyama K, Lin Z, Kan MY (2011) Product review summarization from a deeper perspective. In: Annual international ACM/IEEE joint conference on digital libraries. ACM, pp 311–314

  22. Ma S, Sun X, Lin J, Ren X (2018) A hierarchical end-to-end model for jointly improving text summarization and sentiment classification. In: IJCAI

  23. Markatopoulou F, Mezaris V, Patras I (2016) Deep multi-task learning with label correlation constraint for video concept detection. In: Proceedings of the 2016 ACM on multimedia conference. ACM, pp 501–505

  24. Mason R, Gaska B, Durme BV, Choudhury P, Hart T, Dolan B, Toutanova K, Mitchell M (2016) Microsummarization of online reviews: an experimental study. In: AAAI, pp 3015–3021

  25. McAuley J, Leskovec J (2013) Hidden factors and hidden topics: understanding rating dimensions with review text. In: ACM conference on recommender systems. ACM, pp 165–172

  26. Mei Q, Ling X, Wondra M, Su H, Zhai CX (2007) Topic sentiment mixture: modeling facets and opinions in weblogs. In: Proceedings of the 16th international conference on World Wide Web. ACM, pp 171–180

  27. Mo K, Li S, Zhang Y, Li J, Yang Q (2017) Personalizing a dialogue system with transfer learning. In: The thirty-first AAAI conference on artificial intelligence

  28. Mukherjee A, Liu B (2012) Aspect extraction through semi-supervised modeling. In: ACL, pp 339–348

  29. Nallapati R, Zhou B, Gulcehre C, Xiang B et al (2016) Abstractive text summarization using sequence-to-sequence RNNS and beyond. In: Proceedings of the 20th SIGNLL conference on computational natural language learning. Association for Computational Linguistics, pp 280–290

  30. Papineni K, Roukos S, Ward T, Zhu WJ (2002) BLEU: a method for automatic evaluation of machine translation. In: The 40th annual meeting on association for computational linguistics, pp 311–318

  31. Pasunuru R, Bansal M (2017) Multi-task video captioning with video and entailment generation. In: The 55th annual meeting of the association for computational linguistics, pp 1273–1283

  32. Paulus R, Xiong C, Socher R (2017) A deep reinforced model for abstractive summarization. arXiv preprint arXiv:1705.04304

  33. Popescu AM, Etzioni O (2007) Extracting product features and opinions from reviews. In: Natural language processing and text mining. Springer, pp 9–28

  34. Porteous I, Newman D, Ihler A, Asuncion A, Smyth P, Welling M (2008) Fast collapsed gibbs sampling for latent Dirichlet allocation. In: SIGKDD, pp 569–577

  35. Ranzato MA, Chopra S, Auli M, Zaremba W (2015) Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732

  36. Rush AM, Chopra S, Weston J (2015) A neural attention model for abstractive sentence summarization. In: Proceedings of the 2015 conference on empirical methods in natural language processing. Association for Computational Linguistics, pp 379–389

  37. See A, Liu PJ, Manning CD (2017) Get to the point: summarization with pointer-generator networks. In: Proceedings of the 55th annual meeting of the association for computational linguistics. Association for Computational Linguistics, pp 1073–1083

  38. Shen W, Zhao K, Jiang Y, Wang Y, Bai X, Yuille A (2017) Deepskeleton: learning multi-task scale-associated deep side outputs for object skeleton extraction in natural images. IEEE Trans Image Process 26(11):5298–5311

    MathSciNet  MATH  Google Scholar 

  39. Titov I, McDonald R (2008) Modeling online reviews with multi-grain topic models. In: Proceedings of the 17th international conference on World Wide Web. ACM, pp 111–120

  40. Venugopalan S, Hendricks LA, Mooney R, Saenko K (2016) Improving LSTM-based video description with linguistic knowledge mined from text. In: Proceedings of the conference on empirical methods in natural language processing, pp 1961–1966

  41. Yang M, Mei J, Xu F, Tu W, Lu Z (2016) Discovering author interest evolution in topic modeling. In: Proceedings of the 39th international ACM SIGIR conference on research and development in information retrieval. ACM, pp 801–804

  42. Yang M, Qu Q, Shen Y, Liu Q, Zhao W, Zhu J (2018) Aspect and sentiment aware abstractive review summarization. In: Proceedings of the 27th international conference on computational linguistics, pp 1110–1120

  43. Yang M, Zhao Z, Zhao W, Chen X, Zhu J, Zhou L, Cao Z (2017) Personalized response generation via domain adaptation. In: Proceedings of the 40th international ACM SIGIR conference on research and development in information retrieval. ACM, pp 1021–1024

  44. Yang M, Zhu D, Rashed M, Chow KP (2014) Learning domain-specific sentiment lexicon with supervised sentiment-aware LDA. In: Proceedings of the twenty-first European conference on artificial intelligence (ECAI'14), pp 927–932

  45. Yang Y, Ma Z, Yang Y, Nie F, Tao Shen H (2015) Multitask spectral clustering by exploring intertask correlation. IEEE Trans Cybern 45(5):1083–1094

    Google Scholar 

  46. Yu N, Huang M, Shi Y et al (2016) Product review summarization by exploiting phrase properties. In: Proceedings of the 26th international conference on computational linguistics (COLING), pp 1113–1124

  47. Yuan Y, Lin J, Wang Q (2016) Hyperspectral image classification via multitask joint sparse representation and stepwise MRF optimization. IEEE Trans Cybern 46(12):2966–2977

    Google Scholar 

  48. Zhang L, Zhang Y, Chen Y (2012) Summarizing highly structured documents for effective search interaction. In: SIGIR. ACM

  49. Zhang Q, Levine MD (2016) Robust multi-focus image fusion using multi-task sparse representation and spatial context. IEEE Trans Image Process 25(5):2045–2058

    MathSciNet  MATH  Google Scholar 

  50. Zheng W, Zhu X, Wen G, Zhu Y, Yu H, Ganv J (2018) Unsupervised feature selection by self-paced learning regularization. Pattern Recognit Lett. https://doi.org/10.1016/j.patrec.2018.06.029

    Google Scholar 

  51. Zheng W, Zhu X, Zhu Y, Hu R, Lei C (2017) Dynamic graph learning for spectral feature selection. Multimed Tools Appl 77(22):29739–29755

    Google Scholar 

  52. Zhu X, Zhang S, Hu R, Zhu Y et al (2018) Local and global structure preservation for robust unsupervised spectral feature selection. IEEE Trans Knowl Data Eng 30(3):517–529

    Google Scholar 

  53. Zhu X, Zhang S, Li Y, Zhang J, Yang L, Fang Y (2018) Low-rank sparse subspace for spectral clustering. IEEE Trans Knowl Data Eng. https://ieeexplore.ieee.org/document/8417928

  54. Zhuang L, Jing F, Zhu XY (2006) Movie review mining and summarization. In: Proceedings of the 15th ACM international conference on information and knowledge management. ACM, pp 43–50

Download references

Acknowledgements

The work was partially supported by CAS Pioneer Hundred Talents Program, National Natural Science Foundation of China (No. 61750110516), and Guangdong Natural Science Fund Project (No. 2018A030313017).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Qiang Qu.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yang, M., Qu, Q., Shen, Y. et al. Cross-domain aspect/sentiment-aware abstractive review summarization by combining topic modeling and deep reinforcement learning. Neural Comput & Applic 32, 6421–6433 (2020). https://doi.org/10.1007/s00521-018-3825-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-018-3825-2

Keywords

Navigation