Elamur Research⌕
☰
home / papers / 2021 / Aspect-Controllable Opinion Summarization

Aspect-Controllable Opinion Summarization

Paper · 2021 · Reinald Kim Amplayo, Stefanos Angelidis and Mirella Lapata

Summary

Most opinion summarizers condense many reviews into one generic summary built around the most frequently voiced opinions. That fails users who care about a specific, possibly less-discussed, aspect. The authors present AceSum, an abstractive system whose output can be steered toward one or several aspects, such as a hotel's location or rooms. From an unlabeled review corpus, they build synthetic training data. Each pseudo-summary is paired with input reviews and with aspect controllers at three granularities: document-level aspect codes, aspect-bearing sentences and aspect keywords. A multiple instance learning model induces these controllers using only small sets of seed words per aspect. It uses a new multi-head, max-based pooling step that passes predictions from tokens to sentences to documents. A pretrained T5 model is then fine-tuned on this data. At inference, changing the controllers yields general, single-aspect or multi-aspect summaries. On SPACE (hotels) and OPOSUM+ (multi-domain products), AceSum beats earlier extractive and abstractive systems in both automatic and human evaluation. This makes review summaries more adaptable to individual needs.

Key points

  • Resources and evaluation: Code and data are released (github.com/rktamplayo/AceSum). Evaluation covers SPACE and OPOSUM+, with LexRank, QT and T5-SIMILAR as main baselines.
  • Human quality ratings: In Best-Worst Scaling, AceSum ranked top on informativeness, coherence, conciseness and fluency for both datasets. Example scores on OPOSUM+ were 38.1 for informativeness and 36.3 for coherence.
  • Single-aspect control: On SPACE, 50.9% of AceSum's aspect summaries stayed exclusively on the requested aspect. The figures were 43.8% for QT and 10.6% for T5-SIMILAR, against 64.9% for human-written summaries.
  • Two-aspect control: When asked to cover two aspects, AceSum included both in 61.3% of cases on SPACE and 47.0% on OPOSUM+. QT reached only 10.0% and 18.8%.
  • Pooling ablation: The proposed max-based multi-instance pooling outperformed mean and attention pooling, which did particularly poorly on document-level F1.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓University of EdinburghEdinburgh · United Kingdom255 works · 68,771 citations

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 9,086 worksArtificial Intelligence · 8,889 worksArts and Humanities · 9,296 worksLanguage and Linguistics · 9,206 works

🧭 Topics 1Research subjects and languages the work is about.Summarization · 159 works

Cite

Cite as Reinald Kim Amplayo, Stefanos Angelidis and Mirella Lapata. 2021. Aspect-Controllable Opinion Summarization. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2021.emnlp-main.528

@inproceedings{amplayo2021aspect,
  title = {{Aspect-Controllable Opinion Summarization}},
  author = {Reinald Kim Amplayo, Stefanos Angelidis and Mirella Lapata},
  booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing},
  year = {2021},
  doi = {10.18653/v1/2021.emnlp-main.528},
  url = {https://doi.org/10.18653/v1/2021.emnlp-main.528}
}

References

53 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Reinald Kim Amplayo, Stefanos Angelidis, and Mirella Lapata. 2021. Unsupervised opinion summarization with content planning. In Proceedings of the 35th Conference on Artificial Intelligence, pages 12489–12497. AAAI Press. find
  2. Reinald Kim Amplayo and Mirella Lapata. 2020. Unsupervised opinion summarization with noising and denoising. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1934–1945, Online. Association for Computational Linguistics. find
  3. Stefanos Angelidis, Reinald Kim Amplayo, Yoshihiko Suhara, Xiaolan Wang, and Mirella Lapata. 2021. Extractive Opinion Summarization in Quantized Transformer Spaces. Transactions of the Association for Computational Linguistics, 9:277–293.
  4. Stefanos Angelidis and Mirella Lapata. 2018a. Multiple instance learning networks for fine-grained sentiment analysis. Transactions of the Association for Computational Linguistics, 6:17–31. find
  5. Stefanos Angelidis and Mirella Lapata. 2018b. Summarizing opinions: Aspect extraction meets sentiment prediction and they are both weakly supervised. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3675–3686, Brussels, Belgium. Association for Computa…
  6. Arthur Bražinskas, Mirella Lapata, and Ivan Titov. 2020. Unsupervised opinion summarization as copycat-review generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5151–5169, Online. Association for Computational Linguistics.
  7. In this work, we presented an abstractive approach to aspect-controlled opinion summarization. Key to our model is the induction of aspect controllers which facilitate the creation of a synthetic training Isabel Cachola, Kyle Lo, Arman Cohan, and Daniel dataset and guide summary generation towards t… find
  8. Giuseppe Carenini, Jackie Chi Kit Cheung, and Adam Pauls. 2013. Mutli-document summarization of evaluative text. Computational Intelligence, 29(4):545–576. find
  9. Eric Chu and Peter Liu. 2019. MeanSum: A neural model for unsupervised multi-document abstractive summarization. In Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 1223–1232, Long Beach, California, USA. PMLR. find
  10. DUC 2005: Evaluation of question-focused summarization systems. In Proceedings of the Workshop on Task-Focused Summarization and Question Answering, pages 48–55, Sydney, Australia. Association for Computational Linguistics. find
  11. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
  12. Thomas G Dietterich, Richard H Lathrop, and Tomás Lozano-Pérez. 1997. Solving the multiple instance problem with axis-parallel rectangles. Artificial Intelligence, 89(1-2):31–71. find
  13. Hady Elsahar, Maximin Coavoux, Jos Rozen, and Matthias Gallé. 2021. Self-supervised and controlled multi-document opinion summarization. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1646–1662, Online. Association f… find
  14. Günes Erkan and Dragomir R. Radev. 2004. Lexrank: Graph-based lexical centrality as salience in text summarization. Journal of Artificial Intelligence Research, 22(1):457–479. find
  15. Giuseppe Di Fabbrizio, Amanda Stent, and Robert Gaizauskas. 2014. A hybrid approach to multi-document summarization of opinions in reviews. In Proceedings of the 8th International Natural Language Generation Conference (INLG), pages 54–63, Philadelphia, Pennsylvania, U.S.A. Association for Computati… find
  16. Angela Fan, David Grangier, and Michael Auli. 2018. Controllable abstractive summarization. In Proceedings of the 2nd Workshop on Neural Machine Translation and Generation, pages 45–54, Melbourne, Australia. Association for Computational Linguistics.
  17. Kavita Ganesan, ChengXiang Zhai, and Jiawei Han. 2010. Opinosis: A graph based approach to abstractive summarization of highly redundant opinions. In Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010), pages 340–348, Beijing, China.
  18. Coling 2010 Organizing Committee. find
  19. Sebastian Gehrmann, Falcon Dai, Henry Elder, and Alexander Rush. 2018. End-to-end content and plan selection for data-to-text generation. In Proceedings of the 11th International Conference on Natural Language Generation, pages 46–56, Tilburg University, The Netherlands. Association for Computationa… find
  20. Ruidan He, Wee Sun Lee, Hwee Tou Ng, and Daniel Dahlmeier. 2017. An unsupervised neural attention model for aspect extraction. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 388–397, Vancouver, Canada. Association for Computa…
  21. Minqing Hu and Bing Liu. 2004. Mining and summarizing customer reviews. In Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 168–177, New York, NY, USA. Association for Computing Machinery. find
  22. Minqing Hu and Bing Liu. 2006. Opinion extraction and summarization on the web. In Proceedings of the 21st National Conference on Artificial Intelligence, pages 1621–1624. AAAI Press. find
  23. Jim Keeler and David E. Rumelhart. 1991. A self-organizing integrated segmentation and recognition neural net. In Proceedings of the 4th International Conference on Neural Information Processing Systems, page 496–503, San Francisco, CA, USA. Morgan Kaufmann Publishers Inc. find
  24. Yuta Kikuchi, Graham Neubig, Ryohei Sasano, Hiroya Takamura, and Manabu Okumura. 2016. Controlling output length in neural encoder-decoders. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1328–1338, Austin, Texas. Association for Computational Lingui…
  25. Hyun Duk Kim, Kavita Ganesan, Parikshit Sondhi, and ChengXiang Zhai. 2011. Comprehensive review of opinion summarization. Technical report. find
  26. Diederik P. Kingma and Max Welling. 2014. Autoencoding variational Bayes. In Proceedings of the 3rd International Conference on Learning Representations, Banff, AB. find
  27. Dimitrios Kotzias, Misha Denil, Nando De Freitas, and Padhraic Smyth. 2015. From group to individual labels using deep features. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 597–606, New York, NY, USA. find
  28. Chin-Yew Lin and Eduard Hovy. 2003. Automatic evaluation of summaries using n-gram co-occurrence statistics. In Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, pages 150–157.
  29. Yang Liu and Mirella Lapata. 2019. Text summarization with pretrained encoders. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3730–3740, Hong Kong, China. Assoc… find
  30. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692. find
  31. Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. In International Conference on Learning Representations, New Orleans, LA, USA. find
  32. Jordan J. Louviere, Terry N. Flynn, and A. A. J. Marley. 2015. Best-Worst Scaling: Theory, Methods and Applications. Cambridge University Press. find
  33. Oded Maron and Aparna Lakshmi Ratan. 1998. Multiple-instance learning for natural scene classification. In Proceedings of the Annual International Conference on Machine Learning, volume 98, pages 341–349. find
  34. Julian McAuley, Christopher Targett, Qinfeng Shi, and Anton van den Hengel. 2015. Image-based recommendations on styles and substitutes. In Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, page 43–52, New York, NY, USA. Association for… find
  35. Arjun Mukherjee and Bing Liu. 2012. Aspect extraction through semi-supervised modeling. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 339–348, Jeju Island, Korea. Association for Computational Linguistics. find
  36. Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 188–197, Hong Kong, China. Association for Computational Linguistics. find
  37. Aaron van den Oord, Oriol Vinyals, and Koray Kavukcuoglu. 2017. Neural discrete representation learning. In Proceedings of the 31st International Conference on Neural Information Processing Systems, page 6309–6318, Red Hook, NY, USA. Curran Associates Inc. find
  38. Bo Pang and Lillian Lee. 2008. Opinion mining and sentiment analysis. Foundations and Trends in Information Retrieval, 2(1-2):1–135. find
  39. Bo Pang, Lillian Lee, and Shivakumar Vaithyanathan. 2002. Thumbs up?: Sentiment classification using machine learning techniques. In Proceedings of the ACL-02 Conference on Empirical Methods in Natural Language Processing - Volume 10, pages 79– 86, Stroudsburg, PA, USA. Association for Computational…
  40. Romain Paulus, Caiming Xiong, and Richard Socher. 2018. A deep reinforced model for abstractive summarization. In International Conference on Learning Representations, Vancouver, Canada.
  41. Maria Pontiki, Dimitris Galanis, Haris Papageorgiou, Ion Androutsopoulos, Suresh Manandhar, Mohammad AL-Smadi, Mahmoud Al-Ayyoub, Yanyan Zhao, Bing Qin, Orphée De Clercq, Véronique Hoste, Marianna Apidianaki, Xavier Tannier, Natalia Loukachevitch, Evgeniy Kotelnikov, Nuria Bel, Salud María Jiménez-Z…
  42. Dragomir R Radev, Hongyan Jing, Małgorzata Styś, and Daniel Tam. 2004. Centroid-based summarization of multiple documents. Information Processing and Management, 40(6):919–938. find
  43. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(140):1–67.
  44. Shashi Narayan, Shay B. Cohen, and Mirella Lapata. 2018. Ranking sentences for extractive summarization with reinforcement learning. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Paper…
  45. Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108. find
  46. Jianmo Ni, Jiacheng Li, and Julian McAuley. 2019. Justifying recommendations using distantly-labeled reviews and fine-grained aspects. In Proceedings of the 2019 Conference on Empirical Methods in Abigail See, Peter J. Liu, and Christopher D. Manning. 2017. Get to the point: Summarization with point…
  47. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems, pages 6000–6010, USA. Curran Associates Inc.
  48. Lu Wang and Wang Ling. 2016. Neural network-based abstract generation for opinions and arguments. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 47–57, San Diego, California. Association for Com…
  49. Xiu-Shen Wei, Jianxin Wu, and Zhi-Hua Zhou. 2014. Scalable multi-instance learning. In Proceedings of the 2014 IEEE International Conference on Data Mining, pages 1037–1042, Shenzhen, China. find
  50. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Remi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lho…
  51. Yumo Xu and Mirella Lapata. 2019. Weakly supervised domain detection. Transactions of the Association for Computational Linguistics, 7:581–596. find
  52. Hao Zheng and Mirella Lapata. 2019. Sentence centrality revisited for unsupervised summarization. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 6236–6247, Florence, Italy. Association for Computational Linguistics.
  53. Zhi-Hua Zhou, Yu-Yin Sun, and Yu-Feng Li. 2009. Multi-instance learning by treating instances as non-iid samples. In Proceedings of the 26th Annual International Conference on Machine Learning, pages 1249–1256, Montreal, Quebec, Canada. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/amplayo-2021-aspect-controllable-opinion-summarization/