Abstract
Data-to-text generation is usually defined into two parts: planning how to order and structure the information, and generating a text grammatically correct and fluent, that is faithful to the facts described in the input knowledge base source. A typically knowledge base consists of Resource Description Framework (RDF) triples which describe the entities and their relations. There are plenty of end-to-end solutions proposed to generate natural language descriptions from RDF, however, they require large and noise-free training datasets, lack control over how the text will be generated and there is no guarantee that the generated text verbalizes all and only the input. We address these problems by proposing a modular solution that uses templates and generates multiple texts over the data-to-text generation phases, returning the best one. Our experiments on a real-world dataset demonstrate that our approach generates higher quality texts and outperforms some baseline models regarding BLEU, METEOR, and TER.
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.
Currently there are more than one release of this dataset. We used the first release, the same release used in the 2017 shared task.
- 2.
We used the same preprocessing and the same tools. All scores reported here are calculated in the same way. METEOR and TER scores were rounded to 2 decimal places; BLEU score was not rounded.
References
WebNLG challenge: human evaluation results. Technical report (2018)
Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, pp. 65–72 (2005)
Bergstra, J., Bengio, Y.: Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13(1), 281–305 (2012)
Colin, E., Gardent, C., Mrabet, Y., Narayan, S., Perez-Beltrachini, L.: The WebNLG challenge: generating text from DBPedia data. In: Proceedings of the 9th International Natural Language Generation Conference, pp. 163–167 (2016)
Deemter, K.V., Theune, M., Krahmer, E.: Real versus template-based natural language generation: a false opposition? Comput. Linguist. 31(1), 15–24 (2005)
Distiawan, B., Qi, J., Zhang, R., Wang, W.: GTR-LSTM: a triple encoder for sentence generation from RDF data. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1627–1637 (2018)
Duma, D., Klein, E.: Generating natural language from linked data: unsupervised template extraction. In: Proceedings of the 10th International Conference on Computational Semantics (IWCS 2013)-Long Papers, pp. 83–94 (2013)
Dušek, O., Howcroft, D.M., Rieser, V.: Semantic noise matters for neural natural language generation. arXiv preprint arXiv:1911.03905 (2019)
Ferreira, T.C., van der Lee, C., van Miltenburg, E., Krahmer, E.: Neural data-to-text generation: a comparison between pipeline and end-to-end architectures. arXiv preprint arXiv:1908.09022 (2019)
Ferreira, T.C., Moussallem, D., Krahmer, E., Wubben, S.: Enriching the WebNLG corpus. In: Proceedings of the 11th International Conference on Natural Language Generation, pp. 171–176 (2018)
Gardent, C., Shimorina, A., Narayan, S., Perez-Beltrachini, L.: Creating training corpora for NLG micro-planning. In: 55th Annual Meeting of the Association for Computational Linguistics (ACL) (2017)
Gatt, A., Krahmer, E.: Survey of the state of the art in natural language generation: core tasks, applications and evaluation. J. Artif. Intell. Res. 61, 65–170 (2018)
Gatti, L., van der Lee, C., Theune, M.: Template-based multilingual football reports generation using Wikidata as a knowledge base. In: Proceedings of the 11th International Conference on Natural Language Generation, pp. 183–188 (2018)
Harris, M.D.: Building a large-scale commercial NLG system for an EMR. In: Proceedings of the Fifth International Natural Language Generation Conference, pp. 157–160 (2008)
Heafield, K., Pouzyrevsky, I., Clark, J.H., Koehn, P.: Scalable modified Kneser-Ney language model estimation. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, Sofia, Bulgaria, pp. 690–696, August 2013. https://kheafield.com/papers/edinburgh/estimate_paper.pdf
Jagfeld, G., Jenne, S., Vu, N.T.: Sequence-to-sequence models for data-to-text natural language generation: word- vs. character-based processing and output diversity. arXiv preprint arXiv:1810.04864 (2018)
Jurafsky, D., Martin, J.H.: Speech and Language Processing: An Introduction to Speech Recognition, Computational Linguistics and Natural Language Processing. Prentice Hall, Upper Saddle River (2008)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Kneser, R., Ney, H.: Improved backing-off for M-gram language modeling. In: 1995 International Conference on Acoustics, Speech, and Signal Processing, vol. 1, pp. 181–184. IEEE (1995)
Lehmann, J., et al.: DBpedia-a large-scale, multilingual knowledge base extracted from Wikipedia. Seman. Web 6(2), 167–195 (2015)
Marcheggiani, D., Perez-Beltrachini, L.: Deep graph convolutional encoders for structured data to text generation. arXiv preprint arXiv:1810.09995 (2018)
Marsi, E., Krahmer, E.: Explorations in sentence fusion. In: Proceedings of the Tenth European Workshop on Natural Language Generation (ENLG 2005) (2005)
Moryossef, A., Goldberg, Y., Dagan, I.: Step-by-step: separating planning from realization in neural data-to-text generation. arXiv preprint arXiv:1904.03396 (2019)
Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 311–318. Association for Computational Linguistics (2002)
Reiter, E.: Pipelines and size constraints. Comput. Linguist. 26(2), 251–259 (2000)
Reiter, E., Dale, R.: Building applied natural language generation systems. Nat. Lang. Eng. 3(1), 57–87 (1997)
Snover, M., Dorr, B., Schwartz, R., Micciulla, L., Makhoul, J.: A study of translation edit rate with targeted human annotation. In: Proceedings of Association for Machine Translation in the Americas, vol. 200 (2006)
Zang, H., Wan, X.: A semi-supervised approach for low-resourced text generation. arXiv preprint arXiv:1906.00584 (2019)
Zhu, Y., et al.: Triple-to-text: converting RDF triples into high-quality natural languages via optimizing an inverse KL divergence. In: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 455–464 (2019)
Acknowledgments
This work is partially supported by the FUNCAP SPU 8789771/2017, and the UFC-FASTEF 31/2019.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Mota, A.V., Coelho da Silva, T.L., De Macêdo, J.A.F. (2020). Template-Based Multi-solution Approach for Data-to-Text Generation. In: Darmont, J., Novikov, B., Wrembel, R. (eds) Advances in Databases and Information Systems. ADBIS 2020. Lecture Notes in Computer Science(), vol 12245. Springer, Cham. https://doi.org/10.1007/978-3-030-54832-2_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-54832-2_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-54831-5
Online ISBN: 978-3-030-54832-2
eBook Packages: Computer ScienceComputer Science (R0)