Abstract
Cross-Language Text Summarization generates summaries in a language different from the language of the source documents. Recent methods use information from both languages to generate summaries with the most informative sentences. However, these methods have performance that can vary according to languages, which can reduce the quality of summaries. In this paper, we propose a compressive framework to generate cross-language summaries. In order to analyze performance and especially stability, we tested our system and extractive baselines on a dataset available in four languages (English, French, Portuguese, and Spanish) to generate English and French summaries. An automatic evaluation showed that our method outperformed extractive state-of-art CLTS methods with better and more stable ROUGE scores for all languages.
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.
- 2.
The keyword bonus is defined by the geometric average of all weight arcs in the graph and aims at favoring compressions with several keywords.
- 3.
We used the same configuration for SimFusion and CoRank as described in [3].
- 4.
Unfortunately, the majority of state-of-the-art systems in CLTS are not available. Therefore, we only considered extractive systems in our analysis.
- 5.
We use the same threshold \(\theta \) of 0.5 described in [3] for French-to-English cross-language summaries.
- 6.
The extension of the MultiLing Pilot 2011 dataset is available at: http://dev.termwatch.es/~fresa/CORPUS/TS/.
References
Yao, J., Wan, X., Xiao, J.: Phrase-based compressive cross-language summarization. In: EMNLP, pp. 118–127 (2015)
Wan, X., Luo, F., Sun, X., Huang, S., Yao, J.G.: Cross-language document summarization via extraction and ranking of multiple summaries. Knowl. Inf. Syst. (2018). https://doi.org/10.1007/s10115-018-1152-7
Linhares Pontes, E., Huet, S., Torres-Moreno, J.M., Linhares, A.C.: Cross-language text summarization using sentence and multi-sentence compression. In: Silberztein, M., Atigui, F., Kornyshova, E., Métais, E., Meziane, F. (eds.) NLDB 2018. Lecture Notes in Computer Science, vol. 10859. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-91947-8_48
Giannakopoulos, G., El-Haj, M., Favre, B., Litvak, M., Steinberger, J., Varma, V.: TAC2011 multiling pilot overview. In: 4th Text Analysis Conference TAC (2011)
Wan, X.: Using bilingual information for cross-language document summarization. In: ACL, pp. 1546–1555 (2011)
Moirón, B.V., Tiedemann, J.: Identifying idiomatic expressions using automatic word-alignment. In: EACL 2006 Workshop on Multiword Expressions in a Multilingual Context (2006)
de Caseli, H.M., Ramisch, C., das Graças Volpe Nunes, M., Villavicencio, A.: Alignment-based extraction of multiword expressions. Lang. Resour. Eval. 44, 59–77 (2010)
Manning, C., Surdeanu, M., Bauer, J., Finkel, J., Bethard, S., McClosky, D.: The Stanford CoreNLP natural language processing toolkit. In: 52nd Annual Meeting of the Association for Computational Linguistics (ACL): System Demonstrations, pp. 55–60 (2014)
Linhares Pontes, E., Huet, S., Gouveia da Silva, T., Linhares, A.C., Torres-Moreno, J.M.: Multi-sentence compression with word vertex-labeled graphs and integer linear programming. In: TextGraphs-12: The Workshop on Graph-based Methods for Natural Language Processing, Association for Computational Linguistics (2018)
Filippova, K.: Multi-sentence compression: finding shortest paths in word graphs. In: COLING, pp. 322–330 (2010)
Wan, X., Li, H., Xiao, J.: Cross-language document summarization based on machine translation quality prediction. In: ACL, pp. 917–926 (2010)
Boudin, F., Huet, S., Torres-Moreno, J.M.: A graph-based approach to cross-language multi-document summarization. Polibits 43, 113–118 (2011)
Zhang, J., Zhou, Y., Zong, C.: Abstractive cross-language summarization via translation model enhanced predicate argument structure fusing. IEEE/ACM Trans. Audio Speech Lang. Process. 24, 1842–1853 (2016)
Bing, L., Li, P., Liao, Y., Lam, W., Guo, W., Passonneau, R.J.: Abstractive multi-document summarization via phrase selection and merging. In: ACL, The Association for Computer Linguistics, pp. 1587–1597 (2015)
Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Workshop Text Summarization Branches Out (ACL 2004), pp. 74–81 (2004)
Acknowledgement
This work was granted by the European Project CHISTERA-AMIS ANR-15-CHR2-0001. We also like to acknowledge the support given by the Laboratoire VERIFORM from the École Polytechnique de Montréal and her coordinator Hanifa Boucheneb.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Pontes, E.L., Huet, S., Torres-Moreno, JM. (2018). A Multilingual Study of Compressive Cross-Language Text Summarization. In: Batyrshin, I., Martínez-Villaseñor, M., Ponce Espinosa, H. (eds) Advances in Computational Intelligence. MICAI 2018. Lecture Notes in Computer Science(), vol 11289. Springer, Cham. https://doi.org/10.1007/978-3-030-04497-8_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-04497-8_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-04496-1
Online ISBN: 978-3-030-04497-8
eBook Packages: Computer ScienceComputer Science (R0)