---
title: "Abstractive Document Summarization with a Graph-Based"
description: "The authors argue that earlier neural work ignored saliency , the problem of deciding which parts of a… 40 references, cited by 84 papers here."
authors: ["Jiwei Tan", "Xiaojun Wan", "Jianguo Xiao"]
year: 2017
venue: "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/P17-1108/"
doi: "10.18653/v1/p17-1108"
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/tan-2017-abstractive-document-summarization-graph-based/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/tan-2017-abstractive-document-summarization-graph-based/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2017](https://md.research.elamur.ai/free/en/papers/2017/page/2/) / Abstractive Document Summarization with a Graph-Based Attentional Neural Model

# Abstractive Document Summarization with a Graph-Based Attentional Neural Model

**Authors:** Jiwei Tan, [Xiaojun Wan](https://md.research.elamur.ai/free/en/authors/xiaojun-wan/) and Jianguo Xiao · **Year:** 2017 · **Venue:** [Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2017](https://md.research.elamur.ai/free/en/venues/acl/2017/)) · **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/P17-1108/) · [PDF](https://aclanthology.org/P17-1108.pdf) · [DOI 10.18653/v1/p17-1108](https://doi.org/10.18653/v1/p17-1108) · [OpenAlex](https://openalex.org/W2741375528)

**Citations:** 325 citations (OpenAlex, 2026-10-14) · [84](https://md.research.elamur.ai/free/en/papers/tan-2017-abstractive-document-summarization-graph-based/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
The paper addresses abstractive summarization of whole documents rather than single sentences. At the time, neural abstractive document models still scored below extractive systems on standard benchmarks. The authors argue that earlier neural work ignored **saliency**, the problem of deciding which parts of a source are important. Their model is a hierarchical LSTM encoder-decoder: a word level builds sentence vectors, and a sentence level builds a document vector. Its core addition is a **graph-based attention mechanism**, inspired by graph-ranking extractive methods, that scores sentence importance across the whole document instead of matching input to output only. Their **hierarchical decoding** method also pairs sentence-level beam search with a reference mechanism. This decoder steers output toward bigrams found in the source and keeps track of sentences already generated. Experiments used two large news corpora with human-written summaries. The model beats earlier neural abstractive systems and comes close to strong extractive ones. This matters because it shows abstractive document summarization can compete when saliency and multi-sentence decoding are modeled explicitly.

## Key points
- **Architecture:** a hierarchical encoder-decoder with LSTMs (the Graves 2013 variant) at both word and sentence levels.
  - "\<eos>" closes each sentence and a pseudo-sentence "\<eod>" closes the document.
  - The final "\<eod>" state serves as the document representation.
- **Attention scoring:** the baseline sentence-level attention uses a bilinear function, η(a, b) = aᵀMb, with a learned matrix M. Graph-based attention replaces it with importance scores from a graph-ranking model over the encoded sentences.
- **Decoding:**
  - A distraction mechanism, following Chen et al. (2016), shifts attention to different source sentences as decoding proceeds.
  - Setting γ = 0 and dropping sentence-level beam search gives the "Baseline Decoder" used for comparison.
- **Comparisons:** a Lead3 baseline, a traditional-attention baseline, earlier neural abstractive models, and neural extractive models. Human evaluation was also conducted.
- **Case study:** a Daily Mail article on benefit fraud. The baseline decoder stops too early, repeats a subject phrase, and gets facts wrong (for example, a six-month prison term instead of three). The full method avoids these errors.

## Interesting ideas
- **Reuse extractive ranking inside attention:** sentence-ranking ideas from graph-based extractive summarization can be built into neural attention. This gives the model a document-wide signal of importance, useful wherever a generator must pick key content from long inputs.
- **Reward overlap with the source while decoding:** favoring bigrams that appear in the source is a cheap way to reduce factual errors such as wrong numbers or durations. It could carry over to data-to-text or report generation, where faithfulness matters more than free paraphrase.
- **Make each sentence aware of earlier ones:** letting the decoder see all sentences already generated prevents it from restating the same salient fact. Any multi-sentence generator that tends to loop on one topic could benefit.
- **Force the decoder past its stop token:** when the baseline decoder ended too early, the authors made it continue and found it could still produce relevant content. This simple diagnostic separates a stopping problem from a content problem.
- **Inspect attention heatmaps over sentences:** plotting input-sentence versus output-sentence attention shows whether the model actually finds the important sentences and moves across them. It is a practical sanity check for hierarchical attention models.

*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

- [Peking University](https://md.research.elamur.ai/free/en/universities/peking-university/) — University, Beijing, China · 100 works · 35,618 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,086 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,889 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

🧭 Topics (1): [📝 Summarization](https://md.research.elamur.ai/free/en/topics/summarization/) · 159 works

## Cite

Cite as: Jiwei Tan, Xiaojun Wan and Jianguo Xiao. 2017. Abstractive Document Summarization with a Graph-Based Attentional Neural Model. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{tan2017abstractive,
  title = {{Abstractive Document Summarization with a Graph-Based Attentional Neural Model}},
  author = {Jiwei Tan, Xiaojun Wan and Jianguo Xiao},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2017},
  doi = {10.18653/v1/p17-1108},
  url = {https://doi.org/10.18653/v1/p17-1108}
}
```

- [← previous Unsupervised Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/artetxe-2017-unsupervised-neural-machine-translation/)
- [next → Generating Sentences by Editing Prototypes](https://md.research.elamur.ai/free/en/papers/guu-2017-generating-sentences-editing-prototypes/)
- [↑ back to papers of 2017](https://md.research.elamur.ai/free/en/papers/2017/page/2/)

## References

40 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. 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/). arXiv preprint arXiv:1409.0473 .
2. Ziqiang Cao, Furu Wei, Li Dong, Sujian Li, and Ming Zhou. 2015a. Ranking with recursive neural networks and its application to multi-document summarization. In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, January 25-30, 2015, Austin, Texas, USA.. pages 2153–2159. [find](https://scholar.google.com/scholar?q=Ziqiang+Cao%2C+Furu+Wei%2C+Li+Dong%2C+Sujian+Li%2C+and+Ming+Zhou%2E+2015a%2E+Ranking+with+recursive+neural+networks+and+its+application+to+multi%2Ddocument+summarization%2E+In+Proceedings+of+the+Twenty%2DNinth+AAAI+Con)
3. Ziqiang Cao, Furu Wei, Sujian Li, Wenjie Li, Ming Zhou, and Houfeng Wang. 2015b. Learning summary prior representation for extractive summarization. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Langua… [find](https://scholar.google.com/scholar?q=Ziqiang+Cao%2C+Furu+Wei%2C+Sujian+Li%2C+Wenjie+Li%2C+Ming+Zhou%2C+and+Houfeng+Wang%2E+2015b%2E+Learning+summary+prior+representation+for+extractive+summarization%2E+In+Proceedings+of+the+53rd+Annual+Meeting+of+the+As)
4. Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, pages 1014–1022. [http://aclweb.org/anthology/P13-1100](http://aclweb.org/anthology/P13-1100). [↗](http://aclweb.org/anthology/P13-1100)
5. Harold P Edmundson. 1969. New methods in automatic extracting. Journal of the ACM (JACM) 16(2):264–285. [find](https://scholar.google.com/scholar?q=Harold+P+Edmundson%2E+1969%2E+New+methods+in+automatic+extracting%2E+Journal+of+the+ACM+%28JACM%29+16%282%29%3A264%E2%80%93285%2E)
6. Günes Erkan and Dragomir R. Radev. 2004. Lexrank: Graph-based lexical centrality as salience in text summarization. J. Artif. Intell. Res. (JAIR) 22:457– 479. [find](https://scholar.google.com/scholar?q=Gu%CC%88nes+Erkan+and+Dragomir+R%2E+Radev%2E+2004%2E+Lexrank%3A+Graph%2Dbased+lexical+centrality+as+salience+in+text+summarization%2E+J%2E+Artif%2E+Intell%2E+Res%2E+%28JAIR%29+22%3A457%E2%80%93+479%2E)
7. Alex Graves. 2013. Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850 . [find](https://scholar.google.com/scholar?q=Alex+Graves%2E+2013%2E+Generating+sequences+with+recurrent+neural+networks%2E+arXiv+preprint+arXiv%3A1308%2E0850+%2E)
8. Taher H. Haveliwala. 2002. Topic-sensitive pagerank. In Proceedings of the Eleventh International World Wide Web Conference, WWW 2002, May 7-11, 2002, Honolulu, Hawaii. pages 517–526. [find](https://scholar.google.com/scholar?q=Taher+H%2E+Haveliwala%2E+2002%2E+Topic%2Dsensitive+pagerank%2E+In+Proceedings+of+the+Eleventh+International+World+Wide+Web+Conference%2C+WWW+2002%2C+May+7%2D11%2C+2002%2C+Honolulu%2C+Hawaii%2E+pages+517%E2%80%93526%2E)
9. Jaime G. Carbonell and Jade Goldstein. 1998. The use of mmr, diversity-based reranking for reordering documents and producing summaries. In SIGIR ’98: Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, August 24-28 1998, Melbourne,… [find](https://scholar.google.com/scholar?q=Jaime+G%2E+Carbonell+and+Jade+Goldstein%2E+1998%2E+The+use+of+mmr%2C+diversity%2Dbased+reranking+for+reordering+documents+and+producing+summaries%2E+In+SIGIR+%E2%80%9998%3A+Proceedings+of+the+21st+Annual+International+ACM+)
10. Karl Moritz Hermann, Tomás Kociský, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, and Phil Blunsom. 2015. [Teaching machines to read and comprehend](https://md.research.elamur.ai/free/en/papers/hermann-2015-teaching-machines-read-comprehend/). In Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, December…
11. Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Si Wei, and Hui Jiang. 2016. Distraction-based neural networks for document summarization. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-16). pages 2754–2760. [find](https://scholar.google.com/scholar?q=Qian+Chen%2C+Xiaodan+Zhu%2C+Zhen%2DHua+Ling%2C+Si+Wei%2C+and+Hui+Jiang%2E+2016%2E+Distraction%2Dbased+neural+networks+for+document+summarization%2E+In+Proceedings+of+the+Twenty%2DFifth+International+Joint+Conference+on+A)
12. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural Computation 9(8):1735–1780. [find](https://scholar.google.com/scholar?q=Sepp+Hochreiter+and+Ju%CC%88rgen+Schmidhuber%2E+1997%2E+Long+short%2Dterm+memory%2E+Neural+Computation+9%288%29%3A1735%E2%80%931780%2E)
13. Jianpeng Cheng and Mirella Lapata. 2016. [Neural summarization by extracting sentences and words](https://md.research.elamur.ai/free/en/papers/cheng-2016-neural-summarization-extracting-sentences-words/). In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, pages 484–494. https://doi.org/10.18653/v1/P… [↗](https://doi.org/10.18653/v1/P…)
14. Kit Jackie Chi Cheung and Gerald Penn. 2014. Unsupervised sentence enhancement for automatic summarization. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, pages 775–786. https://doi.org/10.3115/v1/D14-1085… [↗](https://doi.org/10.3115/v1/D14-1085…)
15. Sumit Chopra, Michael Auli, and M. Alexander Rush. 2016. [Abstractive sentence summarization with attentive recurrent neural networks](https://md.research.elamur.ai/free/en/papers/chopra-2016-abstractive-sentence-summarization-attentive-recurrent/). In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Com…
16. Anirban Dasgupta, Ravi Kumar, and Sujith Ravi. 2013. Summarization through submodularity and dispersion. In Proceedings of the 51st Annual Diederik Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 . [find](https://scholar.google.com/scholar?q=Anirban+Dasgupta%2C+Ravi+Kumar%2C+and+Sujith+Ravi%2E+2013%2E+Summarization+through+submodularity+and+dispersion%2E+In+Proceedings+of+the+51st+Annual+Diederik+Kingma+and+Jimmy+Ba%2E+2014%2E+Adam%3A+A+method+for+stocha)
17. Hayato Kobayashi, Masaki Noguchi, and Taichi Yatsuka. 2015. Summarization based on embedding distributions. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, pages 1984–1989. https://doi.org/10.18653/v1/D15-1232. [↗](https://doi.org/10.18653/v1/D15-1232)
18. Chen Li, Xian Qian, and Yang Liu. 2013. Using supervised bigram-based ilp for extractive summarization. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, pages 1004–1013. [http://aclweb.org/an…](http://aclweb.org/an…) [↗](http://aclweb.org/an…)
19. Jiwei Li, Thang Luong, and Dan Jurafsky. 2015. A hierarchical neural autoencoder for paragraphs and documents. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers).… [find](https://scholar.google.com/scholar?q=Jiwei+Li%2C+Thang+Luong%2C+and+Dan+Jurafsky%2E+2015%2E+A+hierarchical+neural+autoencoder+for+paragraphs+and+documents%2E+In+Proceedings+of+the+53rd+Annual+Meeting+of+the+Association+for+Computational+Linguistic)
20. Jiwei Li, Will Monroe, and Dan Jurafsky. 2016. A simple, fast diverse decoding algorithm for neural generation. arXiv preprint arXiv:1611.08562 . [find](https://scholar.google.com/scholar?q=Jiwei+Li%2C+Will+Monroe%2C+and+Dan+Jurafsky%2E+2016%2E+A+simple%2C+fast+diverse+decoding+algorithm+for+neural+generation%2E+arXiv+preprint+arXiv%3A1611%2E08562+%2E)
21. Chin-Yew Lin. 2004. [Rouge: A package for automatic evaluation of summaries](https://md.research.elamur.ai/free/en/papers/lin-2004-rouge-package-automatic-evaluation-summaries/). In Text Summarization Branches Out: Proceedings of the ACL-04 workshop. Barcelona, Spain, volume 8.
22. Ryan T. McDonald. 2007. A study of global inference algorithms in multi-document summarization. In Advances in Information Retrieval, 29th European Conference on IR Research, ECIR 2007, Rome, Italy, April 2-5, 2007, Proceedings. pages 557–564. [find](https://scholar.google.com/scholar?q=Ryan+T%2E+McDonald%2E+2007%2E+A+study+of+global+inference+algorithms+in+multi%2Ddocument+summarization%2E+In+Advances+in+Information+Retrieval%2C+29th+European+Conference+on+IR+Research%2C+ECIR+2007%2C+Rome%2C+Italy%2C+A)
23. Rada Mihalcea and Paul Tarau. 2004. Textrank: Bringing order into text. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing. pages 404–411. [find](https://scholar.google.com/scholar?q=Rada+Mihalcea+and+Paul+Tarau%2E+2004%2E+Textrank%3A+Bringing+order+into+text%2E+In+Proceedings+of+the+2004+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2E+pages+404%E2%80%93411%2E)
24. Lili Mou, Yiping Song, Rui Yan, Ge Li, Lu Zhang, and Zhi Jin. 2016. [Sequence to backward and forward sequences: A content-introducing approach to generative short-text conversation](https://md.research.elamur.ai/free/en/papers/mou-2016-sequence-backward-forward-sequences-content/). In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers.
25. The COLING 2016 [Organizing Committee, pages 3349–3358](https://md.research.elamur.ai/free/en/papers/mou-2016-sequence-backward-forward-sequences-content/). [http://aclweb.org/anthology/C16-1316](http://aclweb.org/anthology/C16-1316). [↗](http://aclweb.org/anthology/C16-1316)
26. Ramesh Nallapati, Feifei Zhai, and Bowen Zhou. 2017. [Summarunner: A recurrent neural network based sequence model for extractive summarization of documents](https://md.research.elamur.ai/free/en/papers/nallapati-2016-summarunner-recurrent-neural-network-based/). In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, February 4-9, 2017, San Francisco, California, USA.. pages 3075–…
27. Ramesh Nallapati, Bowen Zhou, Cicero dos Santos, Caglar Gulcehre, and Bing Xiang. 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, pages… [find](https://scholar.google.com/scholar?q=Ramesh+Nallapati%2C+Bowen+Zhou%2C+Cicero+dos+Santos%2C+Caglar+Gulcehre%2C+and+Bing+Xiang%2E+2016%2E+Abstractive+text+summarization+using+sequence%2Dto%2Dsequence+rnns+and+beyond%2E+In+Proceedings+of+The+20th+SIGNLL+Con)
28. Hitoshi Nishikawa, Kazuho Arita, Katsumi Tanaka, Tsutomu Hirao, Toshiro Makino, and Yoshihiro Matsuo. 2014. Learning to generate coherent summary with discriminative hidden semi-markov model. In Proceedings of COLING 2014. Dublin City University and Association for Computational Linguistics, pages 1… [find](https://scholar.google.com/scholar?q=Hitoshi+Nishikawa%2C+Kazuho+Arita%2C+Katsumi+Tanaka%2C+Tsutomu+Hirao%2C+Toshiro+Makino%2C+and+Yoshihiro+Matsuo%2E+2014%2E+Learning+to+generate+coherent+summary+with+discriminative+hidden+semi%2Dmarkov+model%2E+In+Proce)
29. Lawrence Page, Sergey Brin, Rajeev Motwani, and Terry Winograd. 1999. [The pagerank citation ranking: Bringing order to the web](https://md.research.elamur.ai/free/en/papers/page-1999-pagerank-citation-ranking-bringing/). Technical report, Stanford InfoLab.
30. Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. [Glove: Global vectors for word representation](https://md.research.elamur.ai/free/en/papers/pennington-2014-glove-global-vectors-word-representation/). In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, pages 1532–1543. https://doi.org/10.3115/v1/… [↗](https://doi.org/10.3115/v1/…)
31. Daniele Pighin, Marco Cornolti, Enrique Alfonseca, and Katja Filippova. 2014. Modelling events through memory-based, open-ie patterns for abstractive summarization. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Com… [find](https://scholar.google.com/scholar?q=Daniele+Pighin%2C+Marco+Cornolti%2C+Enrique+Alfonseca%2C+and+Katja+Filippova%2E+2014%2E+Modelling+events+through+memory%2Dbased%2C+open%2Die+patterns+for+abstractive+summarization%2E+In+Proceedings+of+the+52nd+Annual+M)
32. M. Alexander 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. Association for Computational Linguistics, pages 379–389. https://doi.org/10.18653/v1/D… [↗](https://doi.org/10.18653/v1/D…)
33. Rui Sun, Yue Zhang, Meishan Zhang, and Donghong Ji. 2015. Event-driven headline generation. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Co… [find](https://scholar.google.com/scholar?q=Rui+Sun%2C+Yue+Zhang%2C+Meishan+Zhang%2C+and+Donghong+Ji%2E+2015%2E+Event%2Ddriven+headline+generation%2E+In+Proceedings+of+the+53rd+Annual+Meeting+of+the+Association+for+Computational+Linguistics+and+the+7th+Inter)
34. Kapil Thadani and Kathleen McKeown. 2013. Supervised sentence fusion with single-stage inference. In Proceedings of the Sixth International Joint Conference on Natural Language Processing. Asian Federation of Natural Language Processing, pages 1410– 1418. [find](https://scholar.google.com/scholar?q=Kapil+Thadani+and+Kathleen+McKeown%2E+2013%2E+Supervised+sentence+fusion+with+single%2Dstage+inference%2E+In+Proceedings+of+the+Sixth+International+Joint+Conference+on+Natural+Language+Processing%2E+Asian+Feder)
35. Xiaojun Wan. 2010. Towards a unified approach to simultaneous single-document and multi-document summarizations. In Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010). [find](https://scholar.google.com/scholar?q=Xiaojun+Wan%2E+2010%2E+Towards+a+unified+approach+to+simultaneous+single%2Ddocument+and+multi%2Ddocument+summarizations%2E+In+Proceedings+of+the+23rd+International+Conference+on+Computational+Linguistics+%28Colin)
36. Coling 2010 Organizing Committee, pages 1137–1145. [find](https://scholar.google.com/scholar?q=Coling+2010+Organizing+Committee%2C+pages+1137%E2%80%931145%2E)
37. Xiaojun Wan, Jianwu Yang, and Jianguo Xiao. 2007. Manifold-ranking based topic-focused multi-document summarization. In IJCAI 2007, Proceedings of the 20th International Joint Conference on Artificial Intelligence, Hyderabad, India, January 6-12, 2007. pages 2903–2908. [find](https://scholar.google.com/scholar?q=Xiaojun+Wan%2C+Jianwu+Yang%2C+and+Jianguo+Xiao%2E+2007%2E+Manifold%2Dranking+based+topic%2Dfocused+multi%2Ddocument+summarization%2E+In+IJCAI+2007%2C+Proceedings+of+the+20th+International+Joint+Conference+on+Artificial)
38. Kristian Woodsend and Mirella Lapata. 2012. Multiple aspect summarization using integer linear programming. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Association for Computational Linguistics, pages 23… [find](https://scholar.google.com/scholar?q=Kristian+Woodsend+and+Mirella+Lapata%2E+2012%2E+Multiple+aspect+summarization+using+integer+linear+programming%2E+In+Proceedings+of+the+2012+Joint+Conference+on+Empirical+Methods+in+Natural+Language+Process)
39. Jin-ge Yao, Xiaojun Wan, and Jianguo Xiao. 2017. Recent advances in document summarization. Knowledge and Information Systems . [find](https://scholar.google.com/scholar?q=Jin%2Dge+Yao%2C+Xiaojun+Wan%2C+and+Jianguo+Xiao%2E+2017%2E+Recent+advances+in+document+summarization%2E+Knowledge+and+Information+Systems+%2E)
40. Wenpeng Yin and Yulong Pei. 2015. Optimizing sentence modeling and selection for document summarization. In Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, IJCAI 2015, Buenos Aires, Argentina, July 25-31, 2015. pages 1383–1389. [find](https://scholar.google.com/scholar?q=Wenpeng+Yin+and+Yulong+Pei%2E+2015%2E+Optimizing+sentence+modeling+and+selection+for+document+summarization%2E+In+Proceedings+of+the+Twenty%2DFourth+International+Joint+Conference+on+Artificial+Intelligence%2C+)

*Updated 24 October 2026*