---
title: "SQLNet — paper by Xu et al. (2017) — summary and ideas"
description: "The paper addresses NL2SQL: turning a natural-language question plus a table schema… 8.9 points. 43 references, cited by 89 papers here."
authors: ["Xiaojun Xu", "Chang Liu", "Dawn Song"]
year: 2017
venue: "arXiv:1711.04436"
source: "https://arxiv.org/abs/1711.04436"
doi: "10.48550/arxiv.1711.04436"
arxiv: "1711.04436"
licence: "arXiv — non-exclusive license to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/xu-2017-sqlnet-generating-structured-queries-natural/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/xu-2017-sqlnet-generating-structured-queries-natural/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2017](https://md.research.elamur.ai/free/en/papers/2017/page/2/) / SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning

# SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning

**Authors:** [Xiaojun Xu](https://md.research.elamur.ai/free/en/authors/xiaojun-xu/), [Chang Liu](https://md.research.elamur.ai/free/en/authors/chang-liu/) and [Dawn Song](https://md.research.elamur.ai/free/en/authors/dawn-song/) · **Year:** 2017 · **Venue:** arXiv:1711.04436 · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/1711.04436) · [PDF](https://arxiv.org/pdf/1711.04436) · [DOI 10.48550/arxiv.1711.04436](https://doi.org/10.48550/arxiv.1711.04436) · [arXiv 1711.04436](https://arxiv.org/abs/1711.04436) · [OpenAlex](https://openalex.org/W2768409085)

**Citations:** 283 citations (OpenAlex, 2026-10-14) · [89](https://md.research.elamur.ai/free/en/papers/xu-2017-sqlnet-generating-structured-queries-natural/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper addresses NL2SQL: turning a natural-language question plus a table schema into an SQL query. Standard sequence-to-sequence decoders must commit to one linear ordering of the output. Yet WHERE conditions can be listed in any order without changing the result, which makes training sensitive to an arbitrary choice. The earlier Seq2SQL system tried to fix this with reinforcement learning, but gained only about 2%. SQLNet sidesteps the issue. It uses a fixed SQL sketch whose slots form a dependency graph, so each slot is predicted only from the slots it relies on. Two components fill the slots: a sequence-to-set module, which treats conditions as an unordered set, and column attention, which conditions the question encoding on each candidate column. Trained without any reinforcement learning on the crowd-sourced WikiSQL benchmark, SQLNet sets a new state of the art. The work shows that matching model structure to the output's real symmetries can beat reward-based fixes. That matters for natural-language database interfaces that work from the schema alone, without reading table contents.

## Key points
- **Data:** the authors evaluate on WikiSQL, which they describe as the only large-scale NL2SQL dataset. Its training, dev and test splits share no tables, and the main baseline is Seq2SQL (Zhong et al., 2017).
- **Sketch:** the template has a SELECT clause with an aggregation slot and a column slot. It is followed by a WHERE clause made of one or more conditions, each pairing a column, an operator and a value, with conditions joined by AND. VALUE must be a substring of the question, and OP is chosen from {=, \<, >}.
- **Main results:** on the WikiSQL test set, SQLNet reaches 61.5% exact query-match and 68.3% result-match accuracy. These are 7.5 and 8.9 points above Seq2SQL. The abstract cites a broader 9–13% gain over prior art.
- **Re-split experiment:** in a re-organized WikiSQL split, most test tables also appear in training, which mimics practical deployment. Here SQLNet reaches 70.1% execution accuracy, and its lead over Seq2SQL grows by roughly 2 points.
- **Ablation finding:** adding column attention improves accuracy beyond a plain sequence-to-set model.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [🌐 Computer Networks and Communications](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-networks-and-communications/) · 100 works

## Cite

Cite as: Xiaojun Xu, Chang Liu and Dawn Song. 2017. SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning. arXiv:1711.04436.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{xu2017sqlnet,
  title = {{SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning}},
  author = {Xiaojun Xu, Chang Liu and Dawn Song},
  year = {2017},
  doi = {10.48550/arxiv.1711.04436},
  eprint = {1711.04436},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1711.04436}
}
```

- [← previous Question Generation for Question Answering](https://md.research.elamur.ai/free/en/papers/duan-2017-question-generation-question-answering/)
- [next → WASSA-2017 Shared Task on Emotion Intensity](https://md.research.elamur.ai/free/en/papers/mohammad-2017-wassa-2017-shared-task-emotion/)
- [↑ back to papers of 2017](https://md.research.elamur.ai/free/en/papers/2017/page/2/)

## References

43 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Rajeev Alur, Rastislav Bodik, Garvit Juniwal, Milo MK Martin, Mukund Raghothaman, Sanjit A Seshia, Rishabh Singh, Armando Solar-Lezama, Emina Torlak, and Abhishek Udupa. Syntax-guided synthesis. In Formal Methods in Computer-Aided Design (FMCAD), 2013, pp. 1–8. [find](https://scholar.google.com/scholar?q=Rajeev+Alur%2C+Rastislav+Bodik%2C+Garvit+Juniwal%2C+Milo+MK+Martin%2C+Mukund+Raghothaman%2C+Sanjit+A+Seshia%2C+Rishabh+Singh%2C+Armando+Solar%2DLezama%2C+Emina+Torlak%2C+and+Abhishek+Udupa%2E+Syntax%2Dguided+synthesis%2E+In+Fo)
2. I Androutsopoulos, G Ritchie, and P Thanisch. Masque/sql an efficient and portable natural language query interface for relational databases. Database technical paper, Department of AI, University of Edinburgh, 1993. [find](https://scholar.google.com/scholar?q=I+Androutsopoulos%2C+G+Ritchie%2C+and+P+Thanisch%2E+Masque%2Fsql+an+efficient+and+portable+natural+language+query+interface+for+relational+databases%2E+Database+technical+paper%2C+Department+of+AI%2C+University+of+)
3. Ion Androutsopoulos, Graeme D Ritchie, and Peter Thanisch. Natural language interfaces to databases–an introduction. Natural language engineering, 1(1):29–81, 1995. [find](https://scholar.google.com/scholar?q=Ion+Androutsopoulos%2C+Graeme+D+Ritchie%2C+and+Peter+Thanisch%2E+Natural+language+interfaces+to+databases%E2%80%93an+introduction%2E+Natural+language+engineering%2C+1%281%29%3A29%E2%80%9381%2C+1995%2E)
4. Yoav Artzi and Luke Zettlemoyer. Bootstrapping semantic parsers from conversations. In Proceedings of the conference on empirical methods in natural language processing, pp. 421–432. Association for Computational Linguistics, 2011. [find](https://scholar.google.com/scholar?q=Yoav+Artzi+and+Luke+Zettlemoyer%2E+Bootstrapping+semantic+parsers+from+conversations%2E+In+Proceedings+of+the+conference+on+empirical+methods+in+natural+language+processing%2C+pp%2E+421%E2%80%93432%2E+Association+for+C)
5. Yoav Artzi and Luke Zettlemoyer. [Weakly supervised learning of semantic parsers for mapping instructions to actions](https://md.research.elamur.ai/free/en/papers/artzi-2013-weakly-supervised-learning-semantic-parsers/). Transactions of the Association for Computational Linguistics, 1:49–62, 2013. ISSN 2307-387X.
6. Jonathan Berant, Andrew Chou, Roy Frostig, and Percy Liang. [Semantic parsing on freebase from question-answer pairs](https://md.research.elamur.ai/free/en/papers/berant-2013-semantic-parsing-freebase-question-answer/). In EMNLP, 2013.
7. James Bornholt, Emina Torlak, Dan Grossman, and Luis Ceze. Optimizing synthesis with metas-ketches. 51(1):775–788, 2016. [find](https://scholar.google.com/scholar?q=James+Bornholt%2C+Emina+Torlak%2C+Dan+Grossman%2C+and+Luis+Ceze%2E+Optimizing+synthesis+with+metas%2Dketches%2E+51%281%29%3A775%E2%80%93788%2C+2016%2E)
8. Qingqing Cai and Alexander Yates. Large-scale semantic parsing via schema matching and lexicon extension. In ACL, 2013. [find](https://scholar.google.com/scholar?q=Qingqing+Cai+and+Alexander+Yates%2E+Large%2Dscale+semantic+parsing+via+schema+matching+and+lexicon+extension%2E+In+ACL%2C+2013%2E)
9. Xinyun Chen, Chang Liu, Richard Shin, Dawn Song, and Mingcheng Chen. Latent attention for if-then program synthesis. arXiv preprint arXiv:1611.01867, 2016. — [arXiv:1611.01867](https://arxiv.org/abs/1611.01867) [find](https://scholar.google.com/scholar?q=Xinyun+Chen%2C+Chang+Liu%2C+Richard+Shin%2C+Dawn+Song%2C+and+Mingcheng+Chen%2E+Latent+attention+for+if%2Dthen+program+synthesis%2E+arXiv+preprint+arXiv%3A1611%2E01867%2C+2016%2E+%E2%80%94+%5BarXiv%3A1611%2E01867%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1)
10. Li Dong and Mirella Lapata. [Language to logical form with neural attention](https://md.research.elamur.ai/free/en/papers/dong-2016-language-logical-form-neural-attention/). In ACL, 2016.
11. Facebook. Pytorch, 2017. URL [http://pytorch.org/](http://pytorch.org/). [↗](http://pytorch.org/)
12. Alessandra Giordani and Alessandro Moschitti. Translating questions to SQL queries with generative parsers discriminatively reranked. In COLING, 2012. [find](https://scholar.google.com/scholar?q=Alessandra+Giordani+and+Alessandro+Moschitti%2E+Translating+questions+to+SQL+queries+with+generative+parsers+discriminatively+reranked%2E+In+COLING%2C+2012%2E)
13. Ronghang Hu, Jacob Andreas, Marcus Rohrbach, Trevor Darrell, and Kate Saenko. Learning to reason: End-to-end module networks for visual question answering. arXiv preprint arXiv:1704.05526, 2017. [find](https://scholar.google.com/scholar?q=Ronghang+Hu%2C+Jacob+Andreas%2C+Marcus+Rohrbach%2C+Trevor+Darrell%2C+and+Kate+Saenko%2E+Learning+to+reason%3A+End%2Dto%2Dend+module+networks+for+visual+question+answering%2E+arXiv+preprint+arXiv%3A1704%2E05526%2C+2017%2E)
14. Srinivasan Iyer, Ioannis Konstas, Alvin Cheung, Jayant Krishnamurthy, and Luke Zettlemoyer. Learning a neural semantic parser from user feedback. CoRR, abs/1704.08760, 2017. [find](https://scholar.google.com/scholar?q=Srinivasan+Iyer%2C+Ioannis+Konstas%2C+Alvin+Cheung%2C+Jayant+Krishnamurthy%2C+and+Luke+Zettlemoyer%2E+Learning+a+neural+semantic+parser+from+user+feedback%2E+CoRR%2C+abs%2F1704%2E08760%2C+2017%2E)
15. Diederik P. Kingma and Jimmy Ba. abs/1412.[6980, 2014](https://md.research.elamur.ai/free/en/papers/kingma-2014-adam-method-stochastic-optimization/).
16. [Adam: A method for stochastic optimization](https://md.research.elamur.ai/free/en/papers/kingma-2014-adam-method-stochastic-optimization/). Fei Li and HV Jagadish. Constructing an interactive natural language interface for relational databases. Proceedings of the VLDB Endowment, 8(1):73–84, 2014.
17. Yunyao Li, Huahai Yang, and HV Jagadish. Constructing a generic natural language interface for an xml database. In EDBT, volume 3896, pp. 737–754. Springer, 2006. [find](https://scholar.google.com/scholar?q=Yunyao+Li%2C+Huahai+Yang%2C+and+HV+Jagadish%2E+Constructing+a+generic+natural+language+interface+for+an+xml+database%2E+In+EDBT%2C+volume+3896%2C+pp%2E+737%E2%80%93754%2E+Springer%2C+2006%2E)
18. Percy Liang, Michael I Jordan, and Dan Klein. Learning dependency-based compositional semantics. pp. 590–599, 2011. [find](https://scholar.google.com/scholar?q=Percy+Liang%2C+Michael+I+Jordan%2C+and+Dan+Klein%2E+Learning+dependency%2Dbased+compositional+semantics%2E+pp%2E+590%E2%80%93599%2C+2011%2E)
19. Christopher D. Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven J. Bethard, and David McClosky. [The Stanford CoreNLP natural language processing toolkit](https://md.research.elamur.ai/free/en/papers/manning-2014-stanford-corenlp-natural-language-processing/). In Association for Computational Linguistics (ACL) System Demonstrations, pp. 55–60, 2014.
20. Lili Mou, Zhengdong Lu, Hang Li, and Zhi Jin. Coupling distributed and symbolic execution for natural language queries. arXiv preprint arXiv:1612.02741, 2016. — [arXiv:1612.02741](https://arxiv.org/abs/1612.02741) [find](https://scholar.google.com/scholar?q=Lili+Mou%2C+Zhengdong+Lu%2C+Hang+Li%2C+and+Zhi+Jin%2E+Coupling+distributed+and+symbolic+execution+for+natural+language+queries%2E+arXiv+preprint+arXiv%3A1612%2E02741%2C+2016%2E+%E2%80%94+%5BarXiv%3A1612%2E02741%5D%28https%3A%2F%2Farxiv%2Eorg%2Fab)
21. Panupong Pasupat and Percy Liang. [Compositional semantic parsing on semi-structured tables](https://md.research.elamur.ai/free/en/papers/pasupat-2015-compositional-semantic-parsing-semi-structured/). CoRR, abs/1508.00305, 2015.
22. Jeffrey Pennington, Richard Socher, and Christopher Manning. [Glove: Global vectors for word representation](https://md.research.elamur.ai/free/en/papers/pennington-2014-glove-global-vectors-word-representation/). In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp. 1532–1543, 2014.
23. Ana-Maria Popescu, Oren Etzioni, and Henry Kautz. Towards a theory of natural language interfaces to databases. In Proceedings of the 8th international conference on Intelligent user interfaces, pp. 149–157. ACM, 2003. [find](https://scholar.google.com/scholar?q=Ana%2DMaria+Popescu%2C+Oren+Etzioni%2C+and+Henry+Kautz%2E+Towards+a+theory+of+natural+language+interfaces+to+databases%2E+In+Proceedings+of+the+8th+international+conference+on+Intelligent+user+interfaces%2C+pp%2E+1)
24. Ana-Maria Popescu, Alex Armanasu, Oren Etzioni, David Ko, and Alexander Yates. Modern natural language interfaces to databases: Composing statistical parsing with semantic tractability. In Proceedings of the 20th international conference on Computational Linguistics, pp. 141. Association for Computa… [find](https://scholar.google.com/scholar?q=Ana%2DMaria+Popescu%2C+Alex+Armanasu%2C+Oren+Etzioni%2C+David+Ko%2C+and+Alexander+Yates%2E+Modern+natural+language+interfaces+to+databases%3A+Composing+statistical+parsing+with+semantic+tractability%2E+In+Proceedings)
25. P. J. Price. Evaluation of spoken language systems: the atis domain. In Speech and Natural Language: Proceedings of a Workshop Held at Hidden Valley, Pennsylvania, June 24-27,1990, pp. 91–95, 1990. [find](https://scholar.google.com/scholar?q=P%2E+J%2E+Price%2E+Evaluation+of+spoken+language+systems%3A+the+atis+domain%2E+In+Speech+and+Natural+Language%3A+Proceedings+of+a+Workshop+Held+at+Hidden+Valley%2C+Pennsylvania%2C+June+24%2D27%2C1990%2C+pp%2E+91%E2%80%9395%2C+1990%2E)
26. Chris Quirk, Raymond J Mooney, and Michel Galley. [Language to code: Learning semantic parsers for if-this-then-that recipes](https://md.research.elamur.ai/free/en/papers/quirk-2015-language-code-learning-semantic-parsers/). In ACL (1), pp. 878–888, 2015.
27. Siva Reddy, Mirella Lapata, and Mark Steedman. Large-scale semantic parsing without question-answer pairs. Transactions of the Association for Computational Linguistics, 2:377–392, 2014. [find](https://scholar.google.com/scholar?q=Siva+Reddy%2C+Mirella+Lapata%2C+and+Mark+Steedman%2E+Large%2Dscale+semantic+parsing+without+question%2Danswer+pairs%2E+Transactions+of+the+Association+for+Computational+Linguistics%2C+2%3A377%E2%80%93392%2C+2014%2E)
28. Armando Solar-Lezama, Liviu Tancau, Rastislav Bodik, Sanjit Seshia, and Vijay Saraswat. Combinatorial sketching for finite programs. ACM SIGOPS Operating Systems Review, 40(5):404–415, 2006. [find](https://scholar.google.com/scholar?q=Armando+Solar%2DLezama%2C+Liviu+Tancau%2C+Rastislav+Bodik%2C+Sanjit+Seshia%2C+and+Vijay+Saraswat%2E+Combinatorial+sketching+for+finite+programs%2E+ACM+SIGOPS+Operating+Systems+Review%2C+40%285%29%3A404%E2%80%93415%2C+2006%2E)
29. Lappoon R. Tang and Raymond J. Mooney. Using multiple clause constructors in inductive logic programming for semantic parsing. In Proceedings of the 12th European Conference on Machine Learning, pp. 466–477, Freiburg, Germany, 2001. [find](https://scholar.google.com/scholar?q=Lappoon+R%2E+Tang+and+Raymond+J%2E+Mooney%2E+Using+multiple+clause+constructors+in+inductive+logic+programming+for+semantic+parsing%2E+In+Proceedings+of+the+12th+European+Conference+on+Machine+Learning%2C+pp%2E+4)
30. Oriol Vinyals, Meire Fortunato, and Navdeep Jaitly. Pointer networks. In Advances in Neural Information Processing Systems, pp. 2692–2700, 2015a. [find](https://scholar.google.com/scholar?q=Oriol+Vinyals%2C+Meire+Fortunato%2C+and+Navdeep+Jaitly%2E+Pointer+networks%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+pp%2E+2692%E2%80%932700%2C+2015a%2E)
31. Oriol Vinyals, Łukasz Kaiser, Terry Koo, Slav Petrov, Ilya Sutskever, and Geoffrey Hinton. Grammar as a foreign language. In NIPS, 2015b. [find](https://scholar.google.com/scholar?q=Oriol+Vinyals%2C+%C5%81ukasz+Kaiser%2C+Terry+Koo%2C+Slav+Petrov%2C+Ilya+Sutskever%2C+and+Geoffrey+Hinton%2E+Grammar+as+a+foreign+language%2E+In+NIPS%2C+2015b%2E)
32. CoRR, Oriol Vinyals, Samy Bengio, and Manjunath Kudlur. [Order matters: Sequence to sequence for sets](https://md.research.elamur.ai/free/en/papers/vinyals-2015-order-matters-sequence-sequence-sets/). In ICLR, 2016.
33. Chenglong Wang, Alvin Cheung, and Rastislav Bodik. Synthesizing highly expressive sql queries from input-output examples. In Proceedings of the 38th ACM SIGPLAN Conference on Programming Language Design and Implementation, pp. 452–466. ACM, 2017. [find](https://scholar.google.com/scholar?q=Chenglong+Wang%2C+Alvin+Cheung%2C+and+Rastislav+Bodik%2E+Synthesizing+highly+expressive+sql+queries+from+input%2Doutput+examples%2E+In+Proceedings+of+the+38th+ACM+SIGPLAN+Conference+on+Programming+Language+Desi)
34. David HD Warren and Fernando CN Pereira. [An efficient easily adaptable system for interpreting natural language queries](https://md.research.elamur.ai/free/en/papers/warren-1982-efficient-easily-adaptable-system-interpreting/). Computational Linguistics, 8(3-4):110–122, 1982.
35. Yuk Wah Wong and Raymond Mooney. [Learning synchronous grammars for semantic parsing with lambda calculus](https://md.research.elamur.ai/free/en/papers/wong-2007-learning-synchronous-grammars-semantic-parsing/). In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pp. 960–967, Prague, Czech Republic, June 2007. Association for Computational Linguistics.
36. Navid Yaghmazadeh, Yuepeng Wang, Isil Dillig, and Thomas Dillig. Sqlizer: Query synthesis from natural language. In OOPSLA, 2017. [find](https://scholar.google.com/scholar?q=Navid+Yaghmazadeh%2C+Yuepeng+Wang%2C+Isil+Dillig%2C+and+Thomas+Dillig%2E+Sqlizer%3A+Query+synthesis+from+natural+language%2E+In+OOPSLA%2C+2017%2E)
37. Zichao Yang, Phil Blunsom, Chris Dyer, and Wang Ling. Reference-aware language models. arXiv preprint arXiv:1611.01628, 2016. [find](https://scholar.google.com/scholar?q=Zichao+Yang%2C+Phil+Blunsom%2C+Chris+Dyer%2C+and+Wang+Ling%2E+Reference%2Daware+language+models%2E+arXiv+preprint+arXiv%3A1611%2E01628%2C+2016%2E)
38. Pengcheng Yin, Zhengdong Lu, Hang Li, and Ben Kao. Neural enquirer: Learning to query tables with natural language. arXiv preprint arXiv:1512.00965, 2015. — [arXiv:1512.00965](https://arxiv.org/abs/1512.00965) [find](https://scholar.google.com/scholar?q=Pengcheng+Yin%2C+Zhengdong+Lu%2C+Hang+Li%2C+and+Ben+Kao%2E+Neural+enquirer%3A+Learning+to+query+tables+with+natural+language%2E+arXiv+preprint+arXiv%3A1512%2E00965%2C+2015%2E+%E2%80%94+%5BarXiv%3A1512%2E00965%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F15)
39. John M Zelle and Raymond J Mooney. [Learning to parse database queries using inductive logic programming](https://md.research.elamur.ai/free/en/papers/zelle-1996-learning-parse-database-queries-using/). In Proceedings of the national conference on artificial intelligence, pp. 1050– 1055, 1996.
40. Luke S. Zettlemoyer and Michael Collins. Online learning of relaxed ccg grammars for parsing to logical form. In In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL-2007, pp. 678–687, 2007. [find](https://scholar.google.com/scholar?q=Luke+S%2E+Zettlemoyer+and+Michael+Collins%2E+Online+learning+of+relaxed+ccg+grammars+for+parsing+to+logical+form%2E+In+In+Proceedings+of+the+2007+Joint+Conference+on+Empirical+Methods+in+Natural+Language+Pr)
41. Luke S Zettlemoyer and Michael Collins. [Learning to map sentences to logical form: Structured classification with probabilistic categorial grammars](https://md.research.elamur.ai/free/en/papers/zettlemoyer-2012-learning-map-sentences-logical-form/). arXiv preprint arXiv:1207.1420, 2012.
42. Sai Zhang and Yuyin Sun. Automatically synthesizing sql queries from input-output examples. In Automated Software Engineering (ASE), 2013 IEEE/ACM 28th International Conference on, pp. 224–234. [find](https://scholar.google.com/scholar?q=Sai+Zhang+and+Yuyin+Sun%2E+Automatically+synthesizing+sql+queries+from+input%2Doutput+examples%2E+In+Automated+Software+Engineering+%28ASE%29%2C+2013+IEEE%2FACM+28th+International+Conference+on%2C+pp%2E+224%E2%80%93234%2E)
43. Victor Zhong, Caiming Xiong, and Richard Socher. [Seq2sql: Generating structured queries from natural language using reinforcement learning](https://md.research.elamur.ai/free/en/papers/zhong-2017-seq2sql-generating-structured-queries-natural/). arXiv preprint arXiv:1709.00103, 2017.

*Updated 2 November 2026*