Skip to main content
SpringerLink
Log in

Data Synthesis and Iterative Refinement for Neural Semantic Parsing without Annotated Logical Forms

  • Conference paper
  • First Online:
Chinese Computational Linguistics (CCL 2022)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 13603))

Included in the following conference series:

  • 444 Accesses

Abstract

Semantic parsing aims to convert natural language utterances to logical forms. A critical challenge for constructing semantic parsers is the lack of labeled data. In this paper, we propose a data synthesis and iterative refinement framework for neural semantic parsing, which can build semantic parsers without annotated logical forms. We first generate a naive corpus by sampling logic forms from knowledge bases and synthesizing their canonical utterances. Then, we further propose a bootstrapping algorithm to iteratively refine data and model, via a denoising language model and knowledge-constrained decoding. Experimental results show that our approach achieves competitive performance on Geo, ATIS and Overnight datasets in both unsupervised and semi-supervised data settings.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Agrawal, P., Dalmia, A., Jain, P., Bansal, A., Mittal, A.R., Sankaranarayanan, K.: Unified semantic parsing with weak supervision. In: ACL (2019)

    Google Scholar 

  2. Artzi, Y., Zettlemoyer, L.: Weakly supervised learning of semantic parsers for mapping instructions to actions. TACL 1, 49–62 (2013)

    Article  Google Scholar 

  3. Berant, J., Liang, P.: Semantic parsing via paraphrasing. In: ACL (2014)

    Google Scholar 

  4. Berant, J., Chou, A., Frostig, R., Liang, P.: Semantic parsing on freebase from question-answer pairs. In: EMNLP (2013)

    Google Scholar 

  5. Bogin, B., Berant, J., Gardner, M.: Representing schema structure with graph neural networks for text-to-SQL parsing. In: ACL (2019)

    Google Scholar 

  6. Cao, R., Zhu, S., Liu, C., Li, J., Yu, K.: Semantic parsing with dual learning. In: ACL (2019)

    Google Scholar 

  7. Cao, R., et al.: Unsupervised dual paraphrasing for two-stage semantic parsing. In: ACL (2020)

    Google Scholar 

  8. Chang, S., Liu, P., Tang, Y., Huang, J., He, X., Zhou, B.: Zero-shot text-to-SQL learning with auxiliary task. In: AAAI (2020)

    Google Scholar 

  9. Chen, B., Sun, L., Han, X.: Sequence-to-action, end-to-end semantic graph generation for semantic parsing. In: ACL (2018)

    Google Scholar 

  10. Dasigi, P., Gardner, M., Murty, S., Zettlemoyer, L., Hovy, E.H.: Iterative search for weakly supervised semantic parsing. In: NAACL-HLT (2019)

    Google Scholar 

  11. Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (2019)

    Google Scholar 

  12. Dong, L., Lapata, M.: Language to logical form with neural attention. In: ACL (2016)

    Google Scholar 

  13. Dong, L., Lapata, M.: Coarse-to-fine decoding for neural semantic parsing. In: ACL (2018)

    Google Scholar 

  14. Goldman, O., Latcinnik, V., Nave, E., Globerson, A., Berant, J.: Weakly supervised semantic parsing with abstract examples. In: ACL (2018)

    Google Scholar 

  15. Goldwasser, D., Reichart, R., Clarke, J., Roth, D.: Confidence driven unsupervised semantic parsing. In: ACL (2011)

    Google Scholar 

  16. Guo, J., et al.: Towards complex text-to-SQL in cross-domain database with intermediate representation. In: ACL (2019)

    Google Scholar 

  17. Guo, J., et al.: Benchmarking meaning representations in neural semantic parsing. In: EMNLP (2020)

    Google Scholar 

  18. Herzig, J., Berant, J.: Decoupling structure and lexicon for zero-shot semantic parsing. In: EMNLP (2018)

    Google Scholar 

  19. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)

    Article  Google Scholar 

  20. Iyyer, M., Yih, W., Chang, M.-W.: Search-based neural structured learning for sequential question answering. In: ACL (2017)

    Google Scholar 

  21. Jia, R., Liang, P.: Data recombination for neural semantic parsing. In: ACL (2016)

    Google Scholar 

  22. Jie, Z., Lu, W.: Dependency-based hybrid trees for semantic parsing. In: EMNLP (2018)

    Google Scholar 

  23. Kate, R.J., Wong, Y.W., Mooney, R.J.: Learning to transform natural to formal languages. In: IAAI (2005)

    Google Scholar 

  24. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)

    Google Scholar 

  25. Krishnamurthy, J., Dasigi, P., Gardner, M.: Neural semantic parsing with type constraints for semi-structured tables. In: EMNLP (2017)

    Google Scholar 

  26. Lample, G., Ott, M., Conneau, A., Denoyer, L., Ranzato, M.: Phrase-based & neural unsupervised machine translation. In: EMNLP (2018)

    Google Scholar 

  27. Liang, C., Berant, J., Le, Q., Forbus, K.D., Lao, N.: Neural symbolic machines: learning semantic parsers on freebase with weak supervision. In: ACL (2017)

    Google Scholar 

  28. Lu, W., Ng, H.T., Lee, W.S., Zettlemoyer, L.S.: A generative model for parsing natural language to meaning representations. In: EMNLP (2008)

    Google Scholar 

  29. Misra, D., Chang, M.-W., He, X., Yih, W.: Policy shaping and generalized update equations for semantic parsing from denotations. In: EMNLP (2018)

    Google Scholar 

  30. Pasupat, P., Liang, P.: Inferring logical forms from denotations. In: ACL (2016)

    Google Scholar 

  31. Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP (2014)

    Google Scholar 

  32. Poon, H., Domingos, P.M.: Unsupervised semantic parsing. In: EMNLP (2009)

    Google Scholar 

  33. Poon, H.: Grounded unsupervised semantic parsing. In: ACL (2013)

    Google Scholar 

  34. Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019)

    Google Scholar 

  35. Reddy, S., Lapata, M., Steedman, M.: Large-scale semantic parsing without question-answer pairs. Trans. Assoc. Comput. Linguist. 2, 377–392 (2014)

    Article  Google Scholar 

  36. Shin, R., et al.: Constrained language models yield few-shot semantic parsers. In: Moens, M.-F., Huang, X., Specia, L., Yih, S.W. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event/Punta Cana, Dominican Republic, 7–11 November 2021, pp. 7699–7715. Association for Computational Linguistics (2021)

    Google Scholar 

  37. Su, Y., Yan, X.: Cross-domain semantic parsing via paraphrasing. In: EMNLP (2017)

    Google Scholar 

  38. Sun, Y., et al.: Neural semantic parsing in low-resource settings with back-translation and meta-learning. CoRR (2019)

    Google Scholar 

  39. Susanto, R.H., Lu, W.: Semantic parsing with neural hybrid trees. In: AAAI (2017)

    Google Scholar 

  40. Wang, Y., Berant, J., Liang, P.: Building a semantic parser overnight. In: ACL (2015)

    Google Scholar 

  41. Wong, Y.W., Mooney, R.J.: Learning for semantic parsing with statistical machine translation. In: NACL (2006)

    Google Scholar 

  42. Wong, Y.W., Mooney, R.J.: Learning synchronous grammars for semantic parsing with lambda calculus. In: ACL (2007)

    Google Scholar 

  43. Wu, S., et al.: From paraphrasing to semantic parsing: unsupervised semantic parsing via synchronous semantic decoding. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, 1–6 August 2021, pp. 5110–5121. Association for Computational Linguistics (2021)

    Google Scholar 

  44. Xiao, C., Dymetman, M., Gardent, C.: Sequence-based structured prediction for semantic parsing. In: ACL (2016)

    Google Scholar 

  45. Xu, K., Wu, L., Wang, Z., Yu, M., Chen, L., Sheinin, V.: Exploiting rich syntactic information for semantic parsing with graph-to-sequence model. In: EMNLP (2018)

    Google Scholar 

  46. Ye, H., Li, W., Wang, L.: Jointly learning semantic parser and natural language generator via dual information maximization. In: ACL (2019)

    Google Scholar 

  47. Yin, P., Neubig, G.: A syntactic neural model for general-purpose code generation. In: ACL (2017)

    Google Scholar 

  48. Yin, P., Zhou, C., He, J., Neubig, G.: StructVAE: tree-structured latent variable models for semi-supervised semantic parsing. In: ACL (2018)

    Google Scholar 

  49. Zelle, J.M., Mooney, R.J.: Learning to parse database queries using inductive logic programming. In: AAAI (1996)

    Google Scholar 

  50. Zettlemoyer, L.S., Collins, M.: Learning to map sentences to logical form: structured classification with probabilistic categorial grammars. In: UAI (2005)

    Google Scholar 

  51. Zettlemoyer, L.S., Collins, M.: Online learning of relaxed CCG grammars for parsing to logical form. In: EMNLP-CoNLL (2007)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Chinese Information Processing Laboratory, Chinese Academy of Sciences, Beijing, China

    Shan Wu, Bo Chen, Xianpei Han & Le Sun

  2. State Key Laboratory of Computer Science Institute of Software, Chinese Academy of Sciences, Beijing, China

    Xianpei Han & Le Sun

  3. University of Chinese Academy of Sciences, Beijing, China

    Shan Wu

Authors
  1. Shan Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bo Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xianpei Han
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Le Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Le Sun .

Editor information

Editors and Affiliations

  1. Tsinghua University, Beijing, China

    Maosong Sun

  2. Tsinghua University, Beijing, China

    Yang Liu

  3. Harbin Institute of Technology, Harbin, China

    Wanxiang Che

  4. Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China

    Yang Feng

  5. Fudan University, Shanghai, China

    Xipeng Qiu

  6. Beijing Language and Culture University, Beijing, China

    Gaoqi Rao

  7. Chinese Academy of Sciences, Institute of Automation, Beijing, China

    Yubo Chen

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Wu, S., Chen, B., Han, X., Sun, L. (2022). Data Synthesis and Iterative Refinement for Neural Semantic Parsing without Annotated Logical Forms. In: Sun, M., et al. Chinese Computational Linguistics. CCL 2022. Lecture Notes in Computer Science(), vol 13603. Springer, Cham. https://doi.org/10.1007/978-3-031-18315-7_4

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-18315-7_4

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-18314-0

  • Online ISBN: 978-3-031-18315-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation