Elamur Research
☰
home / papers / 2018 / Abstract Meaning Representation for Multi-Document Summarization

Abstract Meaning Representation for Multi-Document Summarization

Written for the Research library (claude-opus-5-5) from the paper text. Original — aclanthology.org/C18-1101.pdf

Summary

Neural abstractive summarizers mostly handle single documents because they need large parallel corpora, which are costly to build for multi-document input. Liao, Lebanoff and Liu test whether Abstract Meaning Representation (AMR) can serve as the intermediate content layer when summarizing clusters of news articles. Their pipeline first selects groups of related sentences, each covering a distinct aspect of the topic. Each sentence is then parsed into an AMR graph (with JAMR or CAMR). The graphs are fused into one source graph by merging identical concepts and coreferent mentions. A summary subgraph is chosen by a feature-based structured prediction model decoded with integer linear programming. Finally, each summary graph is written in PENMAN notation and passed to an AMR-to-text generator. Every stage is trained separately on modest in-domain data. On DUC-04 and TAC-11, the system beats pointer-generator networks given identical input on ROUGE-1 and uses much more novel wording, though the extractive LexRank baseline still scores higher. The study shows AMR is a workable, domain-independent representation for abstractive multi-document summarization.

Key points

  • With the same spectral-clustering input, AMRSumm-Clst reaches ROUGE-1 F of 30.2% vs. 25.6% for Pointer-Generator on DUC-04, and 31.9% vs. 26.2% on TAC-11.
  • Novelty on DUC-04 is measured as the share of summary uni/bi/trigrams found in the source:
    • Pointer-Generator-all: 99.6/95.2/87.2%
    • Human summaries: 85.2/41.6/17.1%
    • AMRSumm-Clst: 84.6/31.3/8.4%
  • Parser quality affects results. JAMR scores about 58% F and CAMR about 63% F on parsing, against an inter-annotator ceiling of roughly 83%. Switching between them shifts ROUGE by about 1–2 points.
  • Oracle (cost-based) decoding adds about 7–10 points of R-1 F and 2–5 points of R-2 F. Sentence selection guided by reference summaries (Concept Cov, VSM) outperforms clustering-based selection.
  • Date and named-entity subtrees are collapsed into "mega-nodes." The authors suggest that simpler, coarser AMR graphs could make summarization more robust.

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

Fields: Machine translation · Natural language processing

Cited by

76 papers of our library cite it (of the 140673 whose bibliographies we read); 5 of them have a page here, 71 not yet.

Cite

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

@inproceedings{liao2018abstract,
  title = {{Abstract Meaning Representation for Multi-Document Summarization}},
  author = {Liao, Kexin and Lebanoff, Logan and Liu, Fei},
  booktitle = {Proceedings of the 27th International Conference on Computational Linguistics},
  year = {2018},
  url = {https://aclanthology.org/C18-1101/}
}

References

62 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Miguel Ballesteros and Yaser Al-Onaizan. 2017. Amr parsing using stack-LSTMs. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). find
  2. Laura Banarescu, Claire Bonial, Shu Cai, Madalina Georgescu, Kira Griffitt, Ulf Hermjakob, Kevin Knight, Philipp Koehn, Martha Palmer, and Nathan Schneider. 2013. Abstract meaning representation for sembanking. In Proceedings of Linguistic Annotation Workshop. find our card
  3. Regina Barzilay, Kathleen R. McKeown, and Michael Elhadad. 1999. Information fusion in the context of multi-document summarization. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL). find
  4. Lidong Bing, Piji Li, Yi Liao, Wai Lam, Weiwei Guo, and Rebecca J. Passonneau. 2015. Abstractive multi-document summarization via phrase selection and merging. In Proceedings of ACL. find
  5. Jan Buys and Phil Blunsom. 2017. Robust incremental neural semantic graph parsing. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL). find
  6. Shu Cai and Kevin Knight. 2013. Smatch: an evaluation metric for semantic feature structures. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL). find
  7. Ziqiang Cao, Furu Wei, Wenjie Li, and Sujian Li. 2018. Faithful to the original: Fact aware neural abstractive summarization. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). find
  8. 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). find
  9. Jackie Chi Kit Cheung and Gerald Penn. 2014. Unsupervised sentence enhancement for automatic summarization. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). find
  10. Marco Damonte, Shay B. Cohen, and Giorgio Satta. 2017. An incremental parser for abstract meaning representation. In Proceedings of EACL. find our card
  11. Günes Erkan and Dragomir R. Radev. 2004. LexRank: Graph-based lexical centrality as salience in text summarization. Journal of Artificial Intelligence Research. find
  12. Giuseppe Di Fabbrizio, Amanda J. Stent, and Robert Gaizauskas. 2014. A hybrid approach to multi-document summarization of opinions in reviews. Proceedings of the 8th International Natural Language Generation Conference (INLG). find
  13. Jeffrey Flanigan, Sam Thomson, Jaime Carbonell, Chris Dyer, and Noah A. Smith. 2014. A discriminative graph-based parser for the abstract meaning representation. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL). find
  14. Jeffrey Flanigan, Chris Dyer, Noah A. Smith, and Jaime Carbonell. 2016. Generation from abstract meaning representation using tree transducers. In Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL). find our card
  15. Kavita Ganesan, ChengXiang Zhai, and Jiawei Han. 2010. Opinosis: A graph-based approach to abstractive summarization of highly redundant opinions. In Proceedings of the International Conference on Computational Linguistics (COLING). find
  16. Albert Gatt and Emiel Krahmer. 2018. Survey of the state of the art in natural language generation: Core tasks, applications and evaluation. Journal of Artificial Intelligence Research, 61:65–170. find
  17. Pierre-Etienne Genest and Guy Lapalme. 2011. Framework for abstractive summarization using text-to-text generation. In Proceedings of ACL Workshop on Monolingual Text-To-Text Generation. find
  18. Shima Gerani, Yashar Mehdad, Giuseppe Carenini, Raymond T. Ng, and Bita Nejat. 2014. Abstractive summarization of product reviews using discourse structure. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). find
  19. Aria Haghighi and Lucy Vanderwende. 2009. Exploring content models for multi-document summarization. In Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL). find
  20. Kai Hong, John M Conroy, Benoit Favre, Alex Kulesza, Hui Lin, and Ani Nenkova. 2014. A repository of state of the art and competitive baseline summaries for generic news summarization. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC). find
  21. Liang Huang, Kai Zhao, and Mingbo Ma. 2017. When to finish? Optimal beam search for neural text generation (modulo beam size). In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). find
  22. Hongyan Jing and Kathleen McKeown. 1999. The decomposition of human-written summary sentences. In Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR). find
  23. Tomasz Jurczyk and Jinho D. Choi. 2015. Semantics-based graph approach to complex question-answering. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop. find
  24. Yuta Kikuchi, Graham Neubig, Ryohei Sasano, Hiroya Takamura, and Manabu Okumura. 2016. Controlling output length in neural encoder-decoders. In Proceedings of EMNLP. find
  25. Ioannis Konstas, Srinivasan Iyer, Mark Yatskar, Yejin Choi, and Luke Zettlemoyer. 2017. Neural amr: Sequence-to-sequence models for parsing and generation. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL). find our card
  26. Chin-Yew Lin. 2004. ROUGE: a package for automatic evaluation of summaries. In Proceedings of ACL Workshop on Text Summarization Branches Out. find
  27. Fei Liu, Jeffrey Flanigan, Sam Thomson, Norman Sadeh, and Noah A. Smith. 2015. Toward abstractive summarization using semantic representations. In Proceedings of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL). find
  28. Jonathan May and Jay Priyadarshi. 2017. SemEval-2017 task 9: Abstract meaning representation parsing and generation. In Proceedings of SemEval. find
  29. Jonathan May. 2016. SemEval-2016 task 8: Meaning representation parsing. In Proceedings of SemEval. find
  30. 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 (CoNLL). find
  31. Ramesh Nallapati, Feifei Zhai, and Bowen Zhou. 2017. SummaRuNNer: A recurrent neural network based sequence model for extractive summarization of documents. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI). find our card
  32. Ani Nenkova and Kathleen McKeown. 2011. Automatic summarization. Foundations and Trends in Information Retrieval. find
  33. Andrew Y. Ng, Michael I. Jordan, and Yair Weiss. 2002. On spectral clustering: Analysis and an algorithm. In Proceedings of the 14th International Conference on Neural Information Processing Systems (NIPS). find
  34. Tatsuro Oya, Yashar Mehdad, Giuseppe Carenini, and Raymond Ng. 2014. A template-based abstractive meeting summarization: Leveraging summary and source text relationships. In Proceedings of the 8th International Natural Language Generation Conference (INLG). find
  35. Xiaoman Pan, Taylor Cassidy, Ulf Hermjakob, Heng Ji, and Kevin Knight. 2015. Unsupervised entity linking with abstract meaning representation. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL). find
  36. Terence Parsons. 1990. Events in the semantics of English. MIT Press. find
  37. Romain Paulus, Caiming Xiong, and Richard Socher. 2017. A deep reinforced model for abstractive summarization. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). find our card
  38. 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 Annual Meeting of the Association for Computational Linguistics (ACL). find
  39. Nima Pourdamghani, Kevin Knight, and Ulf Hermjakob. 2016. Generating english from abstract meaning representations. In Proceedings of the 9th International Natural Language Generation conference (INLG). find our card
  40. Marc’Aurelio Ranzato, Sumit Chopra, Michael Auli, and Wojciech Zaremba. 2016. Sequence level training with recurrent neural networks. In Proceedings of the International Conference on Learning Representations (ICLR). find our card
  41. Ehud Reiter and Robert Dale. 2000. Building Natural Language Generation Systems. Cambridge University Press New York, NY, USA. find
  42. Alexander M. Rush, Sumit Chopra, and Jason Weston. 2015. A neural attention model for sentence summarization. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). find
  43. Mrinmaya Sachan and Eric P. Xing. 2016. Machine comprehension using rich semantic representations. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL). find
  44. Barry Schein. 1993. Plurals and Events. MIT Press. find
  45. Nathan Schneider, Jeffrey Flanigan, and Tim O’Gorman. 2015. The logic of amr: Practical, unified, graph-based sentence semantics for nlp. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorial Abstracts (NAACL). find
  46. Abigail See, Peter J. Liu, and Christopher D. Manning. 2017. Get to the point: Summarization with pointer-generator networks. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL). find
  47. Linfeng Song, Yue Zhang, Xiaochang Peng, Zhiguo Wang, and Daniel Gildea. 2016. Amr-to-text generation as a traveling salesman problem. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). find
  48. Linfeng Song, Xiaochang Peng, Yue Zhang, Zhiguo Wang, and Daniel Gildea. 2017. Amr-to-text generation with synchronous node replacement grammar. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL). find our card
  49. Kaiqiang Song, Lin Zhao, and Fei Liu. 2018. Structure-infused copy mechanisms for abstractive summarization. In Proceedings of the International Conference on Computational Linguistics (COLING). find
  50. Jun Suzuki and Masaaki Nagata. 2017. Cutting-off redundant repeating generations for neural abstractive summarization. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL). find
  51. Ida Szubert, Adam Lopez, and Nathan Schneider. 2018. A structured syntax-semantics interface for english-amr alignment. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). find our card
  52. Sho Takase, Jun Suzuki, Naoaki Okazaki, Tsutomu Hirao, and Masaaki Nagata. 2016. Neural headline generation on abstract meaning representation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). find
  53. Ales Tamchyna, Chris Quirk, and Michel Galley. 2015. A discriminative model for semantics-to-string translation. In Proceedings of the ACL Workshop on Semantics-Driven Statistical Machine Translation (S2MT). find
  54. Jiwei Tan, Xiaojun Wan, and Jianguo Xiao. 2017. Abstractive document summarization with a graph-based attentional neural model. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL). find
  55. Ioannis Tsochantaridis, Thorsten Joachims, Thomas Hofmann, and Yasemin Altun. 2005. Large margin methods for structured and interdependent output variables. Journal of Machine Learning Research, 6:1453–1484. find
  56. Lucy Vanderwende, Hisami Suzuki, Chris Brockett, and Ani Nenkova. 2007. Beyond SumBasic: Task-focused summarization with sentence simplification and lexical expansion. Information Processing and Management, 43(6):1606–1618. find
  57. Chuan Wang, Nianwen Xue, and Sameer Pradhan. 2015a. Boosting transition-based amr parsing with refined actions and auxiliary analyzers. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (ACL-IJCNLP). find our card
  58. Chuan Wang, Nianwen Xue, and Sameer Pradhan. 2015b. A transition-based algorithm for amr parsing. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL). find
  59. Wiki. 2018. Portal:Current events. https://en.wikipedia.org/wiki/Portal:Current events. ↗
  60. Dani Yogatama and Kumiko Tanaka-Ishii. 2009. Multilingual spectral clustering using document similarity propagation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). find
  61. Dani Yogatama, Fei Liu, and Noah A. Smith. 2015. Extractive summarization by maximizing semantic volume. In Proceedings of the Conference on Empirical Methods on Natural Language Processing (EMNLP). find
  62. Qingyu Zhou, Nan Yang, Furu Wei, and Ming Zhou. 2017. Selective encoding for abstractive sentence summarization. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL). find