Abstract
Multi-sentence compression is the task of generating a single sentence from a set of sentences about the same topic. In this work, we explore the use of syntax factor in combination with informativeness and linguistic quality in an Integer Linear Programming framework. Compression candidate paths generated by a word graph are re-ranked using frequent words. Then top k-shortest paths are used as the variables for Integer Linear Programming formulation. Our system improves over state of the art in both English and Vietnamese datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Nenkova, A., Maskey, S., Liu, Y.: Automatic summarization. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts of ACL 2011, pp. 3:1–3:86 (2011)
Genest, P.E., Lapalme, G., Yousfi-Monod, M.: Hextac: the creation of a manual extractive run. Génération de résumés par abstraction (2013)
Filippova, K.: Multi-sentence compression: finding shortest paths in word graphs. In: COLING 2010, 23rd International Conference on Computational Linguistics, Proceedings of the Conference, 23–27 August 2010, pp. 322–330. Beijing, China (2010)
Banerjee, S., Mitra, P., Sugiyama, K.: Multi-document abstractive summarization using ILP based multi-sentence compression. In: Proceedings of the 24th International Conference on Artificial Intelligence, pp. 1208–1214 (2015)
Daumé, III, H., Marcu, D.: A noisy-channel model for document compression. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 449–456 (2002)
Turner, J., Charniak, E.: Supervised and unsupervised learning for sentence compression. In: Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, pp. 290–297 (2005)
Galley, M., McKeown, K.: Lexicalized markov grammars for sentence compression. In: HLT-NAACL, pp. 180–187 (2007)
Clarke, J., Lapata, M.: Global inference for sentence compression: an integer linear programming approach. J. Artif. Intell. Res. 31, 399–429 (2008)
Thadani, K., McKeown, K.: Sentence compression with joint structural inference. In: Proceedings of the Seventeenth Conference on Computational Natural Language Learning, CoNLL 2013, 8–9 August 2013, pp. 65–74. Sofia, Bulgaria (2013)
Boudin, F., Morin, E.: Keyphrase extraction for n-best reranking in multi-sentence compression. In: Human Language Technologies: Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings, June 9–14, 2013, pp. 298–305. Westin Peachtree Plaza Hotel, Atlanta, Georgia, USA (2013)
Mihalcea, R., Tarau, P.: Proceedings of EMNLP 2004, pp. 404–411 (2004)
Luong, A., Tran, N., Ung, V., Nghiem, M.: Word graph-based multi-sentence compression: Re-ranking candidates using frequent words. In: 7th International Conference on Knowledge and Systems Engineering, pp. 55–60 (2015)
Collins, M.: Probabilistic context-free grammars (PCFGs). Lecture Notes (2013)
McKeown, K., Rosenthal, S., Thadani, K., Moore, C.: Time-efficient creation of an accurate sentence fusion corpus. In: Human Language Technologies, pp. 317–320 (2010)
Acknowledgements
This work was supported by the Ho Chi Minh City Department of Science and Technology, Grant Numbers 15/2016/HD-SKHCN.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this chapter
Cite this chapter
Tuan, D.T., Van Chi, N., Nghiem, MQ. (2017). Multi-sentence Compression Using Word Graph and Integer Linear Programming. In: Król, D., Nguyen, N., Shirai, K. (eds) Advanced Topics in Intelligent Information and Database Systems. ACIIDS 2017. Studies in Computational Intelligence, vol 710. Springer, Cham. https://doi.org/10.1007/978-3-319-56660-3_32
Download citation
DOI: https://doi.org/10.1007/978-3-319-56660-3_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-56659-7
Online ISBN: 978-3-319-56660-3
eBook Packages: EngineeringEngineering (R0)