Abstract
In this paper, we present a neural model to map structured table into document-scale descriptive texts. Most existing neural network based approaches encode a table record-by-record and generate long summaries by attentional encoder-decoder model, which leads to two problems. (1) portions of the generated texts are incoherent due to the mismatch between the row and corresponding records. (2) a lot of irrelevant information is described in the generated texts due to the incorrect selection of the redundant records. Our approach addresses both problems by modeling the row representation as an intermediate structure of the table. In the encoding phase, we first learn record-level representation via transformer encoder. Afterwards, we obtain each row’s representation according to their corresponding records’ representation and model row-level dependency via another transformer encoder. In the decoding phase, we first attend to row-level representation to find important rows. Then, we attend to specific records to generate texts. Experiments were conducted on ROTOWIRE, a dataset which aims at producing a document-scale NBA game summary given structured table of game statistics. Our approach improves a strong baseline’s BLEU score from 14.19 to 15.65 (+10.29%). Furthermore, three extractive evaluation metrics and human evaluation also show that our model has the ability to select salient records and the generated game summary is more accurate.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
We abbreviate the statistics table as STAT.
References
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: International Conference on Learning Representations (2015)
Bao, J., et al.: Table-to-text: describing table region with natural language. In: The Thirty-Second AAAI Conference on Artificial Intelligence, pp. 5020–5027. Association for the Advancement of Artificial Intelligence (2018)
Brill, E., Moore, R.C.: An improved error model for noisy channel spelling correction. In: Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics, pp. 286–293. Association for Computational Linguistics (2000)
Cohan, A., et al.: A discourse-aware attention model for abstractive summarization of long documents. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 615–621. Association for Computational Linguistics (2018)
Duchi, J.C., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12, 2121–2159 (2010)
Gulcehre, C., Ahn, S., Nallapati, R., Zhou, B., Bengio, Y.: Pointing the unknown words. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pp. 140–149. Association for Computational Linguistics (2016)
Jain, P., Laha, A., Sankaranarayanan, K., Nema, P., Khapra, M.M., Shetty, S.: A mixed hierarchical attention based encoder-decoder approach for standard table summarization. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 622–627. Association for Computational Linguistics (2018)
Lebret, R., Grangier, D., Auli, M.: Neural text generation from structured data with application to the biography domain. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 1203–1213. Association for Computational Linguistics (2016)
Li, L., Wan, X.: Point precisely: towards ensuring the precision of data in generated texts using delayed copy mechanism. In: Proceedings of the 27th International Conference on Computational Linguistics, pp. 1044–1055. Association for Computational Linguistics (2018)
Liang, P.: Learning executable semantic parsers for natural language understanding. Commun. ACM 59(9), 68–76 (2016)
Liang, P., Jordan, M., Klein, D.: Learning semantic correspondences with less supervision. In: Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, pp. 91–99. Association for Computational Linguistics (2009)
Ling, J., Rush, A.: Coarse-to-fine attention models for document summarization. In: Proceedings of the Workshop on New Frontiers in Summarization, pp. 33–42. Association for Computational Linguistics (2017)
Liu, T., Wang, K., Sha, L., Chang, B., Sui, Z.: Table-to-text generation by structure-aware seq2seq learning. In: The Thirty-Second AAAI Conference on Artificial Intelligence, pp. 4881–4888. Association for the Advancement of Artificial Intelligence (2018)
Luong, T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 1412–1421. Association for Computational Linguistics (2015)
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, pp. 720–730. Association for Computational Linguistics (2016)
Nie, F., Wang, J., Yao, J.G., Pan, R., Lin, C.Y.: Operation-guided neural networks for high fidelity data-to-text generation. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 3879–3889. Association for Computational Linguistics (2018)
Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of 40th Annual Meeting of the Association for Computational Linguistics, pp. 311–318. Association for Computational Linguistics (2002)
Puduppully, R., Dong, L., Lapata, M.: Data-to-text generation with content selection and planning. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 6908–6915. Association for the Advancement of Artificial Intelligence (2019)
Reiter, E.: An architecture for data-to-text systems. In: Proceedings of the Eleventh European Workshop on Natural Language Generation, pp. 97–104. Association for Computational Linguistics (2007)
Sha, L., et al.: Order-planning neural text generation from structured data. In: The Thirty-Second AAAI Conference on Artificial Intelligence, pp. 5414–5421. Association for the Advancement of Artificial Intelligence (2018)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008. Curran Associates Inc., Long Beach (2017)
Wiseman, S., Shieber, S., Rush, A.: Challenges in data-to-document generation. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 2253–2263. Association for Computational Linguistics (2017)
Acknowledgements
We would like to thank the anonymous reviewers for their helpful comments. This work was supported by the National Key R&D Program of China via grant 2018YFB1005103 and National Natural Science Foundation of China (NSFC) via grants 61632011 and 61772156.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Gong, H., Feng, X., Qin, B., Liu, T. (2019). Table-to-Text Generation via Row-Aware Hierarchical Encoder. In: Sun, M., Huang, X., Ji, H., Liu, Z., Liu, Y. (eds) Chinese Computational Linguistics. CCL 2019. Lecture Notes in Computer Science(), vol 11856. Springer, Cham. https://doi.org/10.1007/978-3-030-32381-3_43
Download citation
DOI: https://doi.org/10.1007/978-3-030-32381-3_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32380-6
Online ISBN: 978-3-030-32381-3
eBook Packages: Computer ScienceComputer Science (R0)