Skip to main content
SpringerLink
Log in

Learning number reasoning for numerical table-to-text generation

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

Although the existing numerical table-to-text generation models have achieved remarkable progress, the idea of generating an accurate analysis of the input table is not well explored. Most existing table-to-text generation algorithms for generating table related information only copy the table record directly but ignore reasoning or calculating over table records. One of the key steps to achieve this ability is number reasoning, which refers to do logical reasoning about the numbers from table records. In this paper, we attempt to improve the number reasoning capability of neural table-to-text generation by generating additional mathematical equations from numerical table records. We propose a neural architecture called Neural Table Reasoning Generator (NTRG), with an additional switching gate as well as a specifically designed equation decoder for generating mathematical equations adaptively. Moreover, we present a pre-training strategy for NTRG similar to the mask language model. Empirical results show that NTRG yields new state-of-the-art results on ROTOWIRE. Furthermore, in order to give a quantitative evaluation of the ability of number reasoning, we construct a sentence-level number reasoning dataset. Results demonstrate the superiority of our approaches over strong baselines.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Notes

  1. On publication, we will release our source code and dataset.

  2. In this paper, we only compare each model using the newest evaluation models [22] on ROTOWIRE. Since the test sets of [9] and the evaluation models in [13] are not completely consistent with other works, and some data cannot be obtained, such as the writer information, so no direct comparison is performed.

References

  1. Bai Y, Li Z, Ding N, Shen Y, Zheng HT (2020) Infobox-to-text generation with tree-like planning based attention network. In: Bessiere C (ed) Proceedings of the twenty-ninth international joint conference on artificial intelligence, IJCAI-20, international joint conferences on artificial intelligence organization, pp 3773–3779, main track

  2. Barzilay R, Lapata M (2005) Collective content selection for concept-to-text generation. In: EMNLP, association for computational linguistics, pp 331–338

  3. Devlin J, Chang MW, Lee K, Toutanova K (2018) Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:181004805

  4. Feng X, Sun Y, Qin B, Gong H, Sun Y, Bi W, Liu X, Liu T (2020) Learning to select bi-aspect information for document-scale text content manipulation. In: AAAI, pp 7716–7723

  5. Gong H, Feng X, Qin B, Liu T (2019) Table-to-text generation via row-aware hierarchical encoder. CCL. Springer, Berlin, pp 533–544

    Google Scholar 

  6. Gong H, Feng X, Qin B, Liu T (2019b) Table-to-text generation with effective hierarchical encoder on three dimensions (row, column and time). In: EMNLP-IJCNLP, pp 3134–3143

  7. Gu J, Lu Z, Li H, Li VO (2016) Incorporating copying mechanism in sequence-to-sequence learning. arXiv preprint arXiv:160306393

  8. Huang D, Shi S, Lin CY, Yin J, Ma WY (2016) How well do computers solve math word problems? Large-scale dataset construction and evaluation. In: ACL (volume 1: long papers), pp 887–896

  9. Iso H, Uehara Y, Ishigaki T, Noji H, Aramaki E, Kobayashi I, Miyao Y, Okazaki N, Takamura H (2019) Learning to select, track, and generate for data-to-text. arXiv preprint arXiv:190709699

  10. Kiddon C, Zettlemoyer L, Choi Y (2016) Globally coherent text generation with neural checklist models. EMNLP 2016:329–339

    Google Scholar 

  11. Li L, Wan X (2018) Point precisely: towards ensuring the precision of data in generated texts using delayed copy mechanism. In: COLING, pp 1044–1055

  12. Li Z, Lin Z, Ding N, Zheng HT, Shen Y (2020) Triple-to-text generation with an anchor-to-prototype framework. In: Bessiere C (ed) Proceedings of the twenty-ninth international joint conference on artificial intelligence, IJCAI-20, international joint conferences on artificial intelligence organization, pp 3780–3786, main track

  13. Lin YC, Yang PA, Lee YK, Chuang KT (2016) Generation of conceptual-level text cloud with graph diffusion. In: Proceedings of the 28th conference on computational linguistics and speech processing (ROCLING 2016), pp 402–411

  14. Liu Q, Guan W, Li S, Kawahara D (2019) Tree-structured decoding for solving math word problems. 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 2370–2379

  15. Locascio N, Narasimhan K, DeLeon E, Kushman N, Barzilay R (2016) Neural generation of regular expressions from natural language with minimal domain knowledge. arXiv preprint arXiv:160803000

  16. Luong MT, Pham H, Manning CD (2015) Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:150804025

  17. Mei H, Bansal M, Walter MR (2015) What to talk about and how? Selective generation using LSTMS with coarse-to-fine alignment. arXiv preprint arXiv:150900838

  18. Mikolov T, Sutskever I, Kai C et al (2013) Distributed representations of words and phrases and their compositionality[J]. Adv Neural Inf Process Syst 26

  19. Nie F, Wang J, Yao JG, Pan R, Lin CY (2018) Operations guided neural networks for high fidelity data-to-text generation. arXiv preprint arXiv:180902735

  20. Pearson K (1901) LIII. On lines and planes of closest fit to systems of points in space. Lond Edinb Dublin Philos Mag J Sci 2(11):559–572

    Article  Google Scholar 

  21. Pennington J, Socher R, Manning C (2014) Glove: global vectors for word representation. In: EMNLP, pp 1532–1543

  22. Puduppully R, Dong L, Lapata M (2018) Data-to-text generation with content selection and planning. arXiv preprint arXiv:180900582

  23. Puduppully R, Dong L, Lapata M (2019) Data-to-text generation with entity modeling. arXiv preprint arXiv:190603221

  24. Reiter E, Dale R (1997) Building applied natural language generation systems. Nat Lang Eng 3(1):57–87

    Article  Google Scholar 

  25. Roy S, Vieira T, Roth D (2015) Reasoning about quantities in natural language. Trans Assoc Comput Linguist 3:1–13

    Article  Google Scholar 

  26. Shen X, Chang E, Su H, Niu C, Klakow D (2020) Neural data-to-text generation via jointly learning the segmentation and correspondence. In: Proceedings of the 58th annual meeting of the association for computational linguistics, association for computational linguistics, Online, pp 7155–7165. https://doi.org/10.18653/v1/2020.acl-main.641

  27. Shi S, Wang Y, Lin CY, Liu X, Rui Y (2015) Automatically solving number word problems by semantic parsing and reasoning. In: EMNLP, pp 1132–1142

  28. Wallace E, Wang Y, Li S, Singh S, Gardner M (2019) Do NLP models know numbers? Probing numeracy in embeddings. arXiv preprint arXiv:190907940

  29. Wang L, Zhang D, Gao L, Song J, Guo L, Shen HT (2018) MathDQN: solving arithmetic word problems via deep reinforcement learning. In: AAAI

  30. Wang Y, Liu X, Shi S (2017) Deep neural solver for math word problems. In: EMNLP, pp 845–854

  31. Wang Z, Wang X, An B, Yu D, Chen C (2020) Towards faithful neural table-to-text generation with content-matching constraints. In: Proceedings of the 58th annual meeting of the association for computational linguistics, association for computational linguistics, Online, pp 1072–1086. https://doi.org/10.18653/v1/2020.acl-main.101,

  32. Wiseman S, Shieber SM, Rush AM (2017) Challenges in data-to-document generation. arXiv preprint arXiv:170708052

  33. Zhao C, Walker M, Chaturvedi S (2020) Bridging the structural gap between encoding and decoding for data-to-text generation. In: Proceedings of the 58th annual meeting of the association for computational linguistics, association for computational linguistics, Online, pp 2481–2491. https://doi.org/10.18653/v1/2020.acl-main.224,

Download references

Acknowledgement

We would like to thank the anonymous reviewers and editors for their helpful comments. This work is supported by the National Key R&D Program of China via grant 2020AAA0106502 and National Natural Science Foundation of China (NSFC) via grant 61906053 and Natural Science Foundation of Heilongjiang via grant YQ2019F008.

Author information

Authors and Affiliations

  1. Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, Harbin, China

    Xiaocheng Feng, Heng Gong, Yuyu Chen, Yawei Sun, Bing Qin, Wei Bi, Xiaojiang Liu & Ting Liu

Authors
  1. Xiaocheng Feng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Heng Gong
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yuyu Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yawei Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Bing Qin
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Wei Bi
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Xiaojiang Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Ting Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bing Qin.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Feng, X., Gong, H., Chen, Y. et al. Learning number reasoning for numerical table-to-text generation. Int. J. Mach. Learn. & Cyber. 12, 2269–2280 (2021). https://doi.org/10.1007/s13042-021-01305-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-021-01305-9

Keywords

Search

Navigation