Abstract
The RDF-to-text task has recently gained substantial attention due to continuous growth of Linked Data. In contrast to traditional pipeline models, recent studies have focused on neural models, which are now able to convert a set of RDF triples into text in an end-to-end style with promising results. However, English is the only language widely targeted. We address this research gap by presenting NABU, a multilingual graph-based neural model that verbalizes RDF data to German, Russian, and English. NABU is based on an encoder-decoder architecture, uses an encoder inspired by Graph Attention Networks and a Transformer as decoder. Our approach relies on the fact that knowledge graphs are language-agnostic and they hence can be used to generate multilingual text. We evaluate NABU in monolingual and multilingual settings on standard benchmarking WebNLG datasets. Our results show that NABU outperforms state-of-the-art approaches on English with 66.21 BLEU, and achieves consistent results across all languages on the multilingual scenario with 56.04 BLEU.
D. Moussallem and D. Gnaneshwar—Equal contribution
D. Moussallem, D. Gnaneshwar and T. Castro Ferreira—This work was carried out under the Google Summer of Code 2019.
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
Similar content being viewed by others
Notes
- 1.
- 2.
Not to be confused with RDFS reification.
- 3.
References
Anselma, L., Mazzei, A.: Designing and testing the messages produced by a virtual dietitian. In: Proceedings of the 11th International Conference on Natural Language Generation, Tilburg University, The Netherlands, November 2018, pp. 244–253. Association for Computational Linguistics (2018)
Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., Ives, Z.: DBpedia: a nucleus for a web of open data. In: Aberer, K., et al. (eds.) ASWC/ISWC -2007. LNCS, vol. 4825, pp. 722–735. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-76298-0_52
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)
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 MT and/or Summarization, pp. 65–72. ACL (2005)
Beck, D., Haffari, G., Cohn, T.: Graph-to-sequence learning using gated graph neural networks. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 273–283 (2018)
Belz, A., White, M., Espinosa, D., Kow, E., Hogan, D., Stent, A.: The first surface realisation shared task: overview and evaluation results. In: Proceedings of the 13th European Workshop on Natural Language Generation, Nancy, France, pp. 217–226. Association for Computational Linguistics (2011)
Bouayad-Agha, N., Casamayor, G., Wanner, L.: Natural language generation in the context of the semantic web. Semant. Web 5(6), 493–513 (2014)
Braun, D., Reiter, E., Siddharthan, A.: SaferDrive: an NLG-based behaviour change support system for drivers. Nat. Lang. Eng. 24(4), 551–588 (2018)
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. Association for Computational Linguistics (2018)
Cimiano, P., Lüker, J., Nagel, D., Unger, C.: Exploiting ontology lexica for generating natural language texts from RDF data. In: Proceedings of the 14th European Workshop on Natural Language Generation, Sofia, Bulgaria, August 2013, pp. 10–19. ACL (2013)
Colin, E., Gardent, C., Mrabet, Y., Narayan, S., Perez-Beltrachini, L.: The WebNLG challenge: generating text from DBPedia data. In: Proceedings of the 9th INLG Conference, pp. 163–167 (2016)
Moussallem, D., et al.: RDF2PT: generating Brazilian Portuguese texts from RDF data. In: The 11th Edition of the Language Resources and Evaluation Conference, Miyazaki (Japan), 7–12 May 2018 (2018)
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: IWCS, pp. 83–94 (2013)
Ell, B., Harth, A.: A language-independent method for the extraction of RDF verbalization templates. In: INLG, pp. 26–34 (2014)
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)
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. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 552–562 (2019)
Gardent, C., Shimorina, A., Narayan, S., Perez-Beltrachini, L.: Creating training corpora for NLG micro-planners. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 179–188. Association for Computational Linguistics (2017)
Gardent, C., Shimorina, A., Narayan, S., Perez-Beltrachini, L.: The WebNLG challenge: generating text from RDF data. In: Proceedings of the 10th International Conference on Natural Language Generation, pp. 124–133 (2017)
Gatt, A., Krahmer, E.: Survey of the state of the art in natural language generation: core tasks, applications and evaluation. arXiv preprint arXiv:1703.09902 (2017)
Gehrmann, S., Dai, F., Elder, H., Rush, A.: End-to-end content and plan selection for data-to-text generation. In: Proceedings of the 11th International Conference on Natural Language Generation, Tilburg University, The Netherlands, November 2018, pp. 46–56. Association for Computational Linguistics (2018)
Gkatzia, D., Hastie, H.F., Lemon, O.: Comparing multi-label classification with reinforcement learning for summarisation of time-series data. In: ACL, no. 1, pp. 1231–1240 (2014)
Gu, J., Lu, Z., Li, H., Li, V.O.K.: Incorporating copying mechanism in sequence-to-sequence learning. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, vol. 1, pp. 1631–1640 (2016)
Johnson, M., et al.: Google’s multilingual neural machine translation system: enabling zero-shot translation. Trans. Assoc. Comput. Linguist. 5, 339–351 (2017)
Kaffee, L.-A., et al.: Mind the (language) gap: generation of multilingual Wikipedia summaries from Wikidata for ArticlePlaceholders. In: Gangemi, A., et al. (eds.) ESWC 2018. LNCS, vol. 10843, pp. 319–334. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-93417-4_21
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Kudo, T.: Subword regularization: improving neural network translation models with multiple subword candidates. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 66–75 (2018)
Luong, T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 1412–1421. ACL (2015)
Marcheggiani, D., Perez, L.: Deep graph convolutional encoders for structured data to text generation. In: Proceedings of the 11th International Conference on Natural Language Generation, pp. 1–9. Association for Computational Linguistics (2018)
Mei, H., Bansal, M., Walter, M.R.: What to talk about and how? Selective generation using LSTMs with coarse-to-fine alignment. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, HLT-NAACL 2016, San Diego, California, pp. 720–730. Association for Computational Linguistics (2016)
Mille, S., Belz, A., Bohnet, B., Graham, Y., Pitler, E., Wanner, L.: The first multilingual surface realisation shared task (SR’18): overview and evaluation results. In: Proceedings of the First Workshop on Multilingual Surface Realisation, Melbourne, Australia, July 2018, pp. 1–12. Association for Computational Linguistics (2018)
Mrabet, Y., et al.: Aligning texts and knowledge bases with semantic sentence simplification. In: WebNLG 2016 (2016)
Ngonga Ngomo, A.-C., Röder, M., Moussallem, D., Usbeck, R., Speck, R.: BENGAL: an automatic benchmark generator for entity recognition and linking. In: Proceedings of the 11th International Conference on Natural Language Generation, pp. 339–349 (2018)
Ngonga Ngomo, A.-C., Moussallem, D., Bühman, L.: A holistic natural language generation framework for the semantic web. In: Proceedings of the International Conference Recent Advances in Natural Language Processing, p. 8. ACL (Association for Computational Linguistics) (2019)
Novikova, J., Dusek, O., Rieser, V.: The E2E dataset: new challenges for end-to-end generation. In: Proceedings of the 18th Annual SIGDIAL Meeting on Discourse and Dialogue, Saarbrücken, Germany, pp. 201–206 (2017)
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 (2002)
Popović, M.: chrF++: words helping character n-grams. In: Proceedings of the Second Conference on Machine Translation, pp. 612–618 (2017)
Reiter, E., Dale, R.: Building Natural Language Generation Systems. Cambridge University Press, Cambridge (2000)
Ribeiro, L.F.R., Zhang, Y., Gardent, C., Gurevych, I.: Modeling global and local node contexts for text generation from knowledge graphs. arXiv preprint arXiv:2001.11003 (2020)
Sellam, T., Das, D., Parikh, A.: BLEURT: learning robust metrics for text generation. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, July 2020, pp. 7881–7892. Association for Computational Linguistics (2020)
Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2016, Berlin, Germany, pp. 1715–1725. Association for Computational Linguistics (2016)
Shimorina, A., Khasanova, E., Gardent, C.: Creating a corpus for Russian data-to-text generation using neural machine translation and post-editing. In: Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing, pp. 44–49 (2019)
Sleimi, A., Gardent, C.: Generating paraphrases from DBPedia using deep learning. In: WebNLG 2016, p. 54 (2016)
Tan, X., Ren, Y., He, D., Qin, T., Zhao, Z., Liu, T.-Y.: Multilingual neural machine translation with knowledge distillation. arXiv preprint arXiv:1902.10461 (2019)
Tang, G., Müller, M., Rios, A., Sennrich, R.: Why self-attention? A targeted evaluation of neural machine translation architectures. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 4263–4272 (2018)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)
Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048–2057 (2015)
Acknowledgments
Research funded by the German Federal Ministry of Economics and Technology (BMWI) in the project RAKI (no. 01MD19012D) and by the H2020 KnowGraphs (GA no. 860801). This work also has been supported by the German Federal Ministry of Education and Research (BMBF) within the project DAIKIRI under the grant no 01IS19085B as well as by the German Federal Ministry for Economic Affairs and Energy (BMWi) within the project SPEAKER under the grant no 01MK20011U. Finally, we also would like to thank the funding provided by the Coordination for the Improvement of Higher Education Personnel (CAPES) from Brazil under the grant 88887.367980/2019-00.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Moussallem, D., Gnaneshwar, D., Castro Ferreira, T., Ngonga Ngomo, AC. (2020). NABU – Multilingual Graph-Based Neural RDF Verbalizer. In: Pan, J.Z., et al. The Semantic Web – ISWC 2020. ISWC 2020. Lecture Notes in Computer Science(), vol 12506. Springer, Cham. https://doi.org/10.1007/978-3-030-62419-4_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-62419-4_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-62418-7
Online ISBN: 978-3-030-62419-4
eBook Packages: Computer ScienceComputer Science (R0)