---
title: "Neural Network-Based Abstract Generation for Opinions and"
description: "The paper addresses abstractive summarization of opinionated text. 24.88 BLEU on RottenTomatoes. 35 references, cited by 70 papers here."
authors: ["Lu Wang", "Wang Ling"]
year: 2016
venue: "Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies"
source: "https://aclanthology.org/N16-1007/"
doi: "10.18653/v1/n16-1007"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/wang-2016-neural-network-based-abstract-generation/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2016-neural-network-based-abstract-generation/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2016](https://md.research.elamur.ai/free/en/papers/2016/page/2/) / Neural Network-Based Abstract Generation for Opinions and Arguments

# Neural Network-Based Abstract Generation for Opinions and Arguments

**Authors:** [Lu Wang](https://md.research.elamur.ai/free/en/authors/lu-wang/) and [Wang Ling](https://md.research.elamur.ai/free/en/authors/wang-ling/) · **Year:** 2016 · **Venue:** [Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies](https://md.research.elamur.ai/free/en/venues/naacl/) ([NAACL 2016](https://md.research.elamur.ai/free/en/venues/naacl/2016/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/N16-1007/) · [PDF](https://aclanthology.org/N16-1007.pdf) · [DOI 10.18653/v1/n16-1007](https://doi.org/10.18653/v1/n16-1007) · [OpenAlex](https://openalex.org/W2963721761)

**Citations:** 130 citations (OpenAlex, 2026-10-14) · [70](https://md.research.elamur.ai/free/en/papers/wang-2016-neural-network-based-abstract-generation/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
The paper addresses abstractive summarization of opinionated text. Given many reviews of one movie, or many arguments supporting one debate point, the system writes a single fluent sentence that captures the shared opinion. Earlier opinion summarizers mostly selected existing sentences or glued salient phrases together. Those outputs tend to be redundant, cannot use new words, and may be ungrammatical. Template-based alternatives avoid this but require substantial manual work.

The authors extend the attention-based encoder-decoder from neural MT so it can read multiple input units: a bidirectional LSTM encodes the text, attention locates relevant content, and an LSTM decoder produces the summary. A topic can have dozens of inputs, so during training the model sees only a subset of units, sampled by importance scores from a regression model with a pairwise preference regularizer. Candidate outputs are then re-ranked.

The authors built two new datasets, RottenTomatoes and Idebate. Idebate supports claim generation from arguments, a task introduced here. The system outperforms extractive and abstractive baselines on BLEU, and human judges rated its outputs as more informative and grammatical.

## Key points
- **RottenTomatoes dataset:** 246,164 professional critic reviews for 3,731 movies (about 66 per movie). The gold summary is the editor-written critic consensus. The split is 2,458 / 536 / 737 movies for train / validation / test.
- **Idebate dataset:** 676 debates with 2,259 editor-written claims. Each sentence counts as one argument, giving 17,359 arguments in total. The split is 450 / 67 / 150 debates.
- **BLEU result:** the system reaches 24.88 BLEU on RottenTomatoes, compared with 19.72 for the abstractive system of Ganesan et al. (2010) (Opinosis). ROUGE scores suggest reasonable content coverage.
- **Pipeline:** word embeddings are random or pre-trained (Mikolov et al., 2013) and are updated during training. A BiLSTM encoder with attention (Bahdanau et al., 2014) feeds an LSTM decoder. Importance-based input sampling is used during training, and generated candidates are re-ranked afterwards.
- **Error analysis:**
  - Weaker summaries are often much shorter than the human abstracts.
  - Some summaries get domain facts wrong, such as named entities or numbers. For example, one summary credits the director Cate Shortland as the lead performer.

## Interesting ideas
- **Importance-based sampling of inputs:** instead of encoding every document, train on a subset of input units drawn according to predicted importance. This keeps training time manageable while still exposing the model to varied inputs. It could help any many-to-one generation task with large input sets, such as summarizing comment threads or news clusters.
- **Pairwise preference regularizer:** the importance regressor is trained with an extra term that respects which unit should outrank which. This is a cheap way to inject ranking signal into a scoring model, useful wherever relative order matters more than exact scores.
- **Re-ranking over model scores:** the authors found that picking candidates by the model's own score worked worse than re-ranking with simple heuristics. Generation models can miss task goals like informativeness, so a separate re-ranking step is worth building into any generation pipeline.
- **Editorial content as free gold data:** consensus blurbs and claims written by site editors serve as ready-made reference summaries. Similar editor-curated sources in other languages, including Ukrainian, could supply training data without new annotation.
- **Fact-type error analysis:** checking outputs specifically for wrong entities, roles and numbers revealed a failure that BLEU does not capture. This kind of targeted check suits evaluation of any abstractive system.

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

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,085 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,888 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works

## Cite

Cite as: Lu Wang and Wang Ling. 2016. Neural Network-Based Abstract Generation for Opinions and Arguments. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{wang2016neural,
  title = {{Neural Network-Based Abstract Generation for Opinions and Arguments}},
  author = {Lu Wang and Wang Ling},
  booktitle = {Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  year = {2016},
  doi = {10.18653/v1/n16-1007},
  url = {https://doi.org/10.18653/v1/n16-1007}
}
```

- [← previous Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss](https://md.research.elamur.ai/free/en/papers/plank-2016-multilingual-part-speech-tagging-bidirectional/)
- [next → Concrete Problems in AI Safety](https://md.research.elamur.ai/free/en/papers/amodei-2016-concrete-problems-ai-safety/)
- [↑ back to papers of 2016](https://md.research.elamur.ai/free/en/papers/2016/page/2/)

## References

35 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Gabor Angeli, Percy Liang, and Dan Klein. 2010. [A simple domain-independent probabilistic approach to generation](https://md.research.elamur.ai/free/en/papers/angeli-2010-simple-domain-independent-probabilistic-approach/). In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 502–512. Association for Computational Linguistics.
2. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. [Neural machine translation by jointly learning to align and translate](https://md.research.elamur.ai/free/en/papers/bahdanau-2014-neural-machine-translation-jointly-learning/). CoRR, abs/1409.0473.
3. Lidong Bing, Piji Li, Yi Liao, Wai Lam, Weiwei Guo, and Rebecca Passonneau. 2015. Abstractive multi-document summarization via phrase selection and merging. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natura… [find](https://scholar.google.com/scholar?q=Lidong+Bing%2C+Piji+Li%2C+Yi+Liao%2C+Wai+Lam%2C+Weiwei+Guo%2C+and+Rebecca+Passonneau%2E+2015%2E+Abstractive+multi%2Ddocument+summarization+via+phrase+selection+and+merging%2E+In+Proceedings+of+the+53rd+Annual+Meeting+o)
4. Eugene Charniak and Mark Johnson. 2005. [Coarse-to-fine n-best parsing and maxent discriminative reranking](https://md.research.elamur.ai/free/en/papers/charniak-2005-coarse-fine-n-best-parsing/). In Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, ACL ’05, pages 173–180, Stroudsburg, PA, USA. Association for Computational Linguistics.
5. David Chiang. 2005. [A hierarchical phrase-based model for statistical machine translation](https://md.research.elamur.ai/free/en/papers/chiang-2005-hierarchical-phrase-based-model-statistical/). In Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, pages 263–270. Association for Computational Linguistics.
6. Michael Denkowski and Alon Lavie. 2014. [Meteor universal: Language specific translation evaluation for any target language](https://md.research.elamur.ai/free/en/papers/denkowski-2014-meteor-universal-language-specific-translation/). In Proceedings of the EACL 2014 Workshop on Statistical Machine Translation.
7. Giuseppe Di Fabbrizio, Amanda J Stent, and Robert Gaizauskas. 2014. A hybrid approach to multi-document summarization of opinions in reviews. [find](https://scholar.google.com/scholar?q=Giuseppe+Di+Fabbrizio%2C+Amanda+J+Stent%2C+and+Robert+Gaizauskas%2E+2014%2E+A+hybrid+approach+to+multi%2Ddocument+summarization+of+opinions+in+reviews%2E)
8. INLG 2014, page 54. John Duchi, Elad Hazan, and Yoram Singer. 2011. Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res., 12:2121–2159, July. Günes Erkan and Dragomir R. Radev. 2004. Lexrank: Graph-based lexical centrality as salience in text summarizat… [find](https://scholar.google.com/scholar?q=INLG+2014%2C+page+54%2E+John+Duchi%2C+Elad+Hazan%2C+and+Yoram+Singer%2E+2011%2E+Adaptive+subgradient+methods+for+online+learning+and+stochastic+optimization%2E+J%2E+Mach%2E+Learn%2E+Res%2E%2C+12%3A2121%E2%80%932159%2C+July%2E+Gu%CC%88nes+Erkan)
9. Katja Filippova, Enrique Alfonseca, Carlos A. Colmenares, Lukasz Kaiser, and Oriol Vinyals. 2015. [Sentence compression by deletion with lstms](https://md.research.elamur.ai/free/en/papers/filippova-2015-sentence-compression-deletion-lstms/). In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 360–368, Lisbon, Portugal, September. Association for Comput…
10. Kavita Ganesan, ChengXiang Zhai, and Jiawei Han. 2010. [Opinosis: a graph-based approach to abstractive summarization of highly redundant opinions](https://md.research.elamur.ai/free/en/papers/ganesan-2010-opinosis-graph-based-approach-abstractive/). In Proceedings of the 23rd international conference on computational linguistics, pages 340–348. Association for Computational Linguistics.
11. Shima Gerani, Yashar Mehdad, Giuseppe Carenini, Raymond T. Ng, and Bita Nejat. 2014. [Abstractive summarization of product reviews using discourse structure](https://md.research.elamur.ai/free/en/papers/hermann-2015-teaching-machines-read-comprehend/). In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1602–1613, Doha, Qatar, October. Assoc…
12. 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, KDD ’04, pages 168–177, New York, NY, USA. [find](https://scholar.google.com/scholar?q=Minqing+Hu+and+Bing+Liu%2E+2004%2E+Mining+and+summarizing+customer+reviews%2E+In+Proceedings+of+the+Tenth+ACM+SIGKDD+International+Conference+on+Knowledge+Discovery+and+Data+Mining%2C+KDD+%E2%80%9904%2C+pages+168%E2%80%93177%2C+)
13. ACM. Thorsten Joachims. 2002. Optimizing search engines using clickthrough data. In Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’02, pages 133–142, New York, NY, USA. [find](https://scholar.google.com/scholar?q=ACM%2E+Thorsten+Joachims%2E+2002%2E+Optimizing+search+engines+using+clickthrough+data%2E+In+Proceedings+of+the+Eighth+ACM+SIGKDD+International+Conference+on+Knowledge+Discovery+and+Data+Mining%2C+KDD+%E2%80%9902%2C+pages)
14. ACM. Nal Kalchbrenner and Phil Blunsom. 2013. [Recurrent continuous translation models](https://md.research.elamur.ai/free/en/papers/kalchbrenner-2013-recurrent-continuous-translation-models/). In EMNLP, pages 1700–1709.
15. ACL. Andrej Karpathy and Li Fei-Fei. 2014. [Deep visual-semantic alignments for generating image descriptions](https://md.research.elamur.ai/free/en/papers/karpathy-2014-deep-visual-semantic-alignments-generating/). arXiv preprint arXiv:1412.2306.
16. Ioannis Konstas and Mirella Lapata. 2012. Concept-to-text generation via discriminative reranking. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 369–378, Jeju Island, Korea, July. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ioannis+Konstas+and+Mirella+Lapata%2E+2012%2E+Concept%2Dto%2Dtext+generation+via+discriminative+reranking%2E+In+Proceedings+of+the+50th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+1%3A)
17. Kevin Lerman, Sasha Blair-Goldensohn, and Ryan Mc-Donald. 2009. Sentiment summarization: Evaluating and learning user preferences. In Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics, EACL ’09, pages 514–522, Stroudsburg, PA, USA. Associatio… [find](https://scholar.google.com/scholar?q=Kevin+Lerman%2C+Sasha+Blair%2DGoldensohn%2C+and+Ryan+Mc%2DDonald%2E+2009%2E+Sentiment+summarization%3A+Evaluating+and+learning+user+preferences%2E+In+Proceedings+of+the+12th+Conference+of+the+European+Chapter+of+the+)
18. Fangtao Li, Chao Han, Minlie Huang, Xiaoyan Zhu, Ying-Ju Xia, Shu Zhang, and Hao Yu. 2010. Structure-aware review mining and summarization. In Proceedings of the 23rd International Conference on Computational Linguistics, COLING ’10, pages 653– 661, Stroudsburg, PA, USA. Association for Computationa… [find](https://scholar.google.com/scholar?q=Fangtao+Li%2C+Chao+Han%2C+Minlie+Huang%2C+Xiaoyan+Zhu%2C+Ying%2DJu+Xia%2C+Shu+Zhang%2C+and+Hao+Yu%2E+2010%2E+Structure%2Daware+review+mining+and+summarization%2E+In+Proceedings+of+the+23rd+International+Conference+on+Compu)
19. Chin-Yew Lin and Eduard Hovy. 2003. [Automatic evaluation of summaries using n-gram co-occurrence statistics](https://md.research.elamur.ai/free/en/papers/lin-2003-automatic-evaluation-summaries-n-gram/). In Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1, pages 71–78.
20. Christopher Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven Bethard, and David McClosky. 2014. [The stanford corenlp natural language processing toolkit](https://md.research.elamur.ai/free/en/papers/manning-2014-stanford-corenlp-natural-language-processing/). In Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 55–60, Baltimore, Ma…
21. Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. [Efficient estimation of word representations in vector space](https://md.research.elamur.ai/free/en/papers/mikolov-2013-efficient-estimation-word-representations-vector/). CoRR, abs/1301.3781.
22. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. [Bleu: a method for automatic evaluation of machine translation](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/). In Proceedings of the 40th annual meeting on association for computational linguistics, pages 311–318. Association for Computational Linguistics.
23. Michael J. Paul, ChengXiang Zhai, and Roxana Girju. 2010. Summarizing contrastive viewpoints in opinionated text. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, EMNLP ’10, pages 66–76, Stroudsburg, PA, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Michael+J%2E+Paul%2C+ChengXiang+Zhai%2C+and+Roxana+Girju%2E+2010%2E+Summarizing+contrastive+viewpoints+in+opinionated+text%2E+In+Proceedings+of+the+2010+Conference+on+Empirical+Methods+in+Natural+Language+Process)
24. Dragomir R. Radev. 2001. Experiments in single and multidocument summarization using mead. In In First Document Understanding Conference. [find](https://scholar.google.com/scholar?q=Dragomir+R%2E+Radev%2E+2001%2E+Experiments+in+single+and+multidocument+summarization+using+mead%2E+In+In+First+Document+Understanding+Conference%2E)
25. Alexander M. Rush, Sumit Chopra, and Jason Weston. 2015. A neural attention model for abstractive sentence summarization. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 379–389, Lisbon, Portugal, September. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Alexander+M%2E+Rush%2C+Sumit+Chopra%2C+and+Jason+Weston%2E+2015%2E+A+neural+attention+model+for+abstractive+sentence+summarization%2E+In+Proceedings+of+the+2015+Conference+on+Empirical+Methods+in+Natural+Language)
26. Ruben Sipos, Pannaga Shivaswamy, and Thorsten Joachims. 2012. Large-margin learning of submodular summarization models. In Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, EACL ’12, pages 224–233, Stroudsburg, PA, USA. Association for Compu… [find](https://scholar.google.com/scholar?q=Ruben+Sipos%2C+Pannaga+Shivaswamy%2C+and+Thorsten+Joachims%2E+2012%2E+Large%2Dmargin+learning+of+submodular+summarization+models%2E+In+Proceedings+of+the+13th+Conference+of+the+European+Chapter+of+the+Association)
27. Alex Smola and Vladimir Vapnik. 1997. Support vector regression machines. Advances in neural information processing systems, 9:155–161. [find](https://scholar.google.com/scholar?q=Alex+Smola+and+Vladimir+Vapnik%2E+1997%2E+Support+vector+regression+machines%2E+Advances+in+neural+information+processing+systems%2C+9%3A155%E2%80%93161%2E)
28. Philip J. Stone, Dexter C. Dunphy, Marshall S. Smith, and Daniel M. Ogilvie. 1966. The General Inquirer: A Computer Approach to Content Analysis. [find](https://scholar.google.com/scholar?q=Philip+J%2E+Stone%2C+Dexter+C%2E+Dunphy%2C+Marshall+S%2E+Smith%2C+and+Daniel+M%2E+Ogilvie%2E+1966%2E+The+General+Inquirer%3A+A+Computer+Approach+to+Content+Analysis%2E)
29. MIT Press, Cambridge, MA. Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014a. Sequence to sequence learning with neural networks. [find](https://scholar.google.com/scholar?q=MIT+Press%2C+Cambridge%2C+MA%2E+Ilya+Sutskever%2C+Oriol+Vinyals%2C+and+Quoc+V%2E+Le%2E+2014a%2E+Sequence+to+sequence+learning+with+neural+networks%2E)
30. In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, December 8-13 2014, Montreal, Quebec, Canada, pages 3104–3112. [find](https://scholar.google.com/scholar?q=In+Advances+in+Neural+Information+Processing+Systems+27%3A+Annual+Conference+on+Neural+Information+Processing+Systems+2014%2C+December+8%2D13+2014%2C+Montreal%2C+Quebec%2C+Canada%2C+pages+3104%E2%80%933112%2E)
31. Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014b. Sequence to sequence learning with neural networks. CoRR, abs/1409.3215. [find](https://scholar.google.com/scholar?q=Ilya+Sutskever%2C+Oriol+Vinyals%2C+and+Quoc+V%2E+Le%2E+2014b%2E+Sequence+to+sequence+learning+with+neural+networks%2E+CoRR%2C+abs%2F1409%2E3215%2E)
32. Lu Wang and Claire Cardie. 2013. Domain-independent abstract generation for focused meeting summarization. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1395–1405, Sofia, Bulgaria, August. Association for Computational Lingu… [find](https://scholar.google.com/scholar?q=Lu+Wang+and+Claire+Cardie%2E+2013%2E+Domain%2Dindependent+abstract+generation+for+focused+meeting+summarization%2E+In+Proceedings+of+the+51st+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28V)
33. Lu Wang, Hema Raghavan, Claire Cardie, and Vittorio Castelli. 2014. Query-focused opinion summarization for user-generated content. In Proceedings of COL-ING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, pages 1660– 1669, Dublin, Ireland, August. Dublin City… [find](https://scholar.google.com/scholar?q=Lu+Wang%2C+Hema+Raghavan%2C+Claire+Cardie%2C+and+Vittorio+Castelli%2E+2014%2E+Query%2Dfocused+opinion+summarization+for+user%2Dgenerated+content%2E+In+Proceedings+of+COL%2DING+2014%2C+the+25th+International+Conference+on)
34. Theresa Wilson, Janyce Wiebe, and Paul Hoffmann. 2005. [Recognizing contextual polarity in phrase-level sentiment analysis](https://md.research.elamur.ai/free/en/papers/wilson-2005-recognizing-contextual-polarity-phrase-level/). In Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, HLT ’05, pages 347–354, Stroudsburg, PA, USA. Association for…
35. Li Zhuang, Feng Jing, and Xiao-Yan Zhu. 2006. Movie review mining and summarization. In Proceedings of the 15th ACM International Conference on Information and Knowledge Management, CIKM ’06, pages 43–50, New York, NY, USA. ACM. [find](https://scholar.google.com/scholar?q=Li+Zhuang%2C+Feng+Jing%2C+and+Xiao%2DYan+Zhu%2E+2006%2E+Movie+review+mining+and+summarization%2E+In+Proceedings+of+the+15th+ACM+International+Conference+on+Information+and+Knowledge+Management%2C+CIKM+%E2%80%9906%2C+pages+43)

*Updated 24 October 2026*