Abstract
Numerous web applications rely on databases, yet the traditional database interface often proves inconvenient for effective data utilization. It is crucial to address the significant demand from a vast number of end users who seek the ability to input their requirements and obtain query results effortlessly. Natural Language (NL) Interfaces to Databases (NLIDBs) with interactive query mechanisms make databases accessible to end users and simultaneously retain user confidence in the results. This paper proposes an approach called IKnow-SQL for building interactive NLIDBs. IKnow-SQL introduces a unified framework for translation models to improve accuracy and increase interactivity. Specifically, IKnow-SQL first employs an underlying translation model to parse the semantics of a given NL query. By evaluating the model behavior, IKnow-SQL then recognizes the parts of the model output that may require human intervention. Next, IKnow-SQL presents clarifying questions to solicit and memorize user feedback until a polished result is obtained. Extensive experiments are performed to study IKnow-SQL on the public benchmark. The results show that the translation models can be effectively improved using IKnow-SQL with less user feedback.
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.
In accordance with [11], model predictions are the weighted sum of target embeddings over output probabilities.
- 2.
We use the terms exact-match accuracy and translation accuracy interchangeably.
References
Androutsopoulos, I., et al.: Natural language interfaces to databases - an introduction. Nat. Lang. Eng. 1(1), 29–81 (1995)
Baik, C., et al.: Bridging the semantic gap with SQL query logs in natural language interfaces to databases. In: ICDE (2019)
Bogin, B., et al.: Representing schema structure with graph neural networks for text-to-SQL parsing. In: ACL (2019)
Cao, R., et al.: LGESQL: line graph enhanced text-to-SQL model with mixed local and non-local relations. In: ACL (2021)
Castaldo, N., Daniel, F., Matera, M., Zaccaria, V.: Conversational data exploration. In: Bakaev, M., Frasincar, F., Ko, I.-Y. (eds.) ICWE 2019. LNCS, vol. 11496, pp. 490–497. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-19274-7_34
Chaurasia, S., et al.: Dialog for language to code. In: IJCNLP, pp. 175–180 (2017)
Desolda, G., et al.: Rapid prototyping of chatbots for data exploration. In: BCNC, pp. 5–10 (2021)
Fan, Y., et al.: Gar: a generate-and-rank approach for natural language to SQL translation. In: ICDE (2023)
Feng, L., Lu, H.: Integrating database and world wide web technologies. WWWJ 1(2), 73–86 (1998)
Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: ICML, vol. 48, pp. 1050–1059 (2016)
Goyal, K., et al.: Differentiable scheduled sampling for credit assignment. In: ACL, pp. 366–371 (2017)
Grave, E., et al.: Improving neural language models with a continuous cache. In: ICLR (2017)
Guo, J., et al.: Towards complex text-to-SQL in cross-domain database with intermediate representation. In: ACL (2019)
Gur, I., et al.: DialSQL: dialogue based structured query generation. In: ACL (2018)
He, H., et al.: Towards deeper understanding of the search interfaces of the deep web. WWWJ 2, 133–155 (2007)
He, L., et al.: Human-in-the-loop parsing. In: EMNLP, pp. 2337–2342 (2016)
Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. In: ICLR (2017)
Li, F., Jagadish, H.V.: Constructing an interactive natural language interface for relational databases. PVLDB 8(1), 73–84 (2014)
Li, J., et al.: Graphix-T5: mixing pre-trained transformers with graph-aware layers for text-to-SQL parsing. In: AAAI, pp. 13076–13084 (2023)
Lin, X.V., et al.: Bridging textual and tabular data for cross-domain text-to-SQL semantic parsing. In: EMNLP (2020)
Nakatsuji, M., et al.: Knowledge-aware response selection with semantics underlying multi-turn open-domain conversations. In: World Wide Web, pp. 1–16 (2023)
Niehues, J., et al.: Modeling confidence in sequence-to-sequence models. In: INLG, pp. 575–583 (2019)
OpenAI: GPT-4 technical report. CoRR (2023)
Pourreza, M., Rafiei, D.: DIN-SQL: decomposed in-context learning of text-to-SQL with self-correction. CoRR (2023)
Saha, D., et al.: ATHENA: an ontology-driven system for natural language querying over relational data stores. PVLDB 9(12), 1209–1220 (2016)
Scholak, T., et al.: PICARD: parsing incrementally for constrained auto-regressive decoding from language models. In: EMNLP (2021)
Sen, J., et al.: ATHENA++: natural language querying for complex nested SQL queries. PVLDB 13(11), 2747–2759 (2020)
Shi, P., et al.: Learning contextual representations for semantic parsing with generation-augmented pre-training. In: AAAI (2021)
Simitsis, A., et al.: Précis: from unstructured keywords as queries to structured databases as answers. PVLDB 17(1), 117–149 (2008)
Su, Y., et al.: Natural language interfaces with fine-grained user interaction: a case study on web APIs. In: SIGIR, pp. 855–864 (2018)
Sukhbaatar, S., et al.: End-to-end memory networks. In: NeurIPS, pp. 2440–2448 (2015)
Touvron, H., et al.: LLaMA: open and efficient foundation language models. CoRR (2023)
Wang, B., et al.: RAT-SQL: relation-aware schema encoding and linking for text-to-SQL parsers. In: ACL (2020)
Xu, X., et al.: SQLNet: generating structured queries from natural language without reinforcement learning. CoRR (2017)
Yao, Z., et al.: Interactive semantic parsing for if-then recipes via hierarchical reinforcement learning. In: AAAI, pp. 2547–2554 (2019)
Yao, Z., et al.: Model-based interactive semantic parsing: a unified framework and a text-to-SQL case study. In: EMNLP, pp. 5446–5457 (2019)
Yu, T., et al.: TypeSQL: knowledge-based type-aware neural text-to-SQL generation. In: NAACL (2018)
Yu, T., et al.: CoSQL: a conversational text-to-SQL challenge towards cross-domain natural language interfaces to databases. In: EMNLP (2019)
Zettlemoyer, L.S., Collins, M.: Learning to map sentences to logical form: structured classification with probabilistic categorial grammars. In: UAI (2005)
Zhang, R., et al.: Editing-based SQL query generation for cross-domain context-dependent questions. In: EMNLP, pp. 5337–5348 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Fan, Y. et al. (2023). An Integrated Interactive Framework for Natural Language to SQL Translation. In: Zhang, F., Wang, H., Barhamgi, M., Chen, L., Zhou, R. (eds) Web Information Systems Engineering – WISE 2023. WISE 2023. Lecture Notes in Computer Science, vol 14306. Springer, Singapore. https://doi.org/10.1007/978-981-99-7254-8_50
Download citation
DOI: https://doi.org/10.1007/978-981-99-7254-8_50
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-7253-1
Online ISBN: 978-981-99-7254-8
eBook Packages: Computer ScienceComputer Science (R0)