Abstract
We present a novel supervised approach to sentence compression, based on classification and removal of word sequences generated from subtrees of the original sentence dependency tree. Our system may use any known classifier like Support Vector Machines or Logistic Model Tree to identify word sequences that can be removed without compromising the grammatical correctness of the compressed sentence. We trained our system using several classifiers on a small annotated dataset of 100 sentences, which included around 1500 manually labeled subtrees (removal candidates) represented by 25 features. The highest cross-validation classification accuracy of 80% was obtained with the SMO (Normalized Poly Kernel) algorithm. We evaluated the readability and the informativeness of the sentences compressed by the SMO-based classification model with the help of human raters using a separate benchmark dataset of 200 sentences.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Complete sentences and single words that are prepositions, wh-words, pronouns, and forms of the “to be” verb are not saved in the list of removal candidates.
- 2.
All syntax features are calculated using the dependency syntax tree, except for the last one, is obtained from the constituency parse tree.
- 3.
We use “LEAF”type for a single word.
- 4.
We use “null” for the non-NEs.
- 5.
References
Berg-Kirkpatrick, T., Gillick, D., Klein, D.: Jointly learning to extract and compress. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, vol. 1, pp. 481–490. Association for Computational Linguistics (2011)
Clarke, J., Lapata, M.: Global inference for sentence compression: an integer linear programming approach. J. Artif. Intell. Res. 31, 399–429 (2008)
Cohn, T., Lapata, M.: Large margin synchronous generation and its application to sentence compression. In: EMNLP-CoNLL, pp. 73–82 (2007)
Cohn, T., Lapata, M.: Sentence compression beyond word deletion. In: Proceedings of the 22nd International Conference on Computational Linguistics, vol. 1, pp. 137–144. Association for Computational Linguistics (2008)
Colmenares, C.A., Litvak, M., Mantrach, A., Silvestri, F.: HEADS: headline generation as sequence prediction using an abstract feature-rich space. In: North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT 2015), pp. 133–142 (2015)
Corston-Oliver, S.: Text compaction for display on very small screens. In: Proceedings of the NAACL Workshop on Automatic Summarization, pp. 89–98. Citeseer (2001)
Filippova, K., Alfonseca, E., Colmenares, C.A., Kaiser, L., Vinyals, O.: Sentence compression by deletion with LSTMs. In: EMNLP, pp. 360–368 (2015)
Filippova, K., Strube, M.: Dependency tree based sentence compression. In: Proceedings of the Fifth International Natural Language Generation Conference, pp. 25–32. Association for Computational Linguistics (2008)
Frank, E., Hall, M.A., Witten, I.H.: The WEKA workbench. online appendix for “data mining: Practical machine learning tools and techniques", 4th edn. Morgan Kaufmann (2016)
Galley, M., McKeown, K.: Lexicalized markov grammars for sentence compression. In: HLT-NAACL, pp. 180–187 (2007)
Jing, H.: Sentence reduction for automatic text summarization. In: Proceedings of the Sixth Conference on Applied Natural Language Processing, pp. 310–315. Association for Computational Linguistics (2000)
Knight, K., Marcu, D.: Statistics-based summarization-step one: sentence compression. In: AAAI/IAAI, vol. 2000, pp. 703–710 (2000)
Knight, K., Marcu, D.: Summarization beyond sentence extraction: a probabilistic approach to sentence compression. Artif. Intell. 139(1), 91–107 (2002)
Lin, C.Y.: Improving summarization performance by sentence compression: a pilot study. In: Proceedings of the Sixth International Workshop on Information Retrieval with Asian Languages, vol. 11, pp. 1–8. Association for Computational Linguistics (2003)
Manning, C.D., Surdeanu, M., Bauer, J., Finkel, J.R., Bethard, S., McClosky, D.: The stanford corenlp natural language processing toolkit. In: ACL (System Demonstrations), pp. 55–60 (2014)
McDonald, R.T.: Discriminative sentence compression with soft syntactic evidence. In: EACL (2006)
Sidhaye, P., Cheung, J.C.K.: Indicative tweet generation: an extractive summarization problem? In: EMNLP, pp. 138–147 (2015)
Vandeghinste, V., Pan, Y.: Sentence compression for automated subtitling: a hybrid approach. In: Proceedings of the ACL workshop on Text Summarization, pp. 89–95 (2004)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 Springer Nature Switzerland AG
About this paper
Cite this paper
Churkin, E., Last, M., Litvak, M., Vanetik, N. (2023). Sentence Compression as a Supervised Learning with a Rich Feature Space. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2018. Lecture Notes in Computer Science, vol 13397. Springer, Cham. https://doi.org/10.1007/978-3-031-23804-8_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-23804-8_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23803-1
Online ISBN: 978-3-031-23804-8
eBook Packages: Computer ScienceComputer Science (R0)