---
title: "SpreadsheetCoder — paper by Chen et al. (2021)"
description: "This paper argues that real spreadsheets are semi-structured: rows and columns depend on each… 54 references, cited by 24 papers here."
authors: ["Xinyun Chen", "Petros Maniatis", "Rishabh Singh", "Charles Sutton", "Hanjun Dai", "Max Lin", "Denny Zhou"]
year: 2021
venue: "arXiv:2106.15339"
source: "https://arxiv.org/abs/2106.15339"
doi: "10.48550/arxiv.2106.15339"
arxiv: "2106.15339"
licence: "arXiv — non-exclusive licence to distribute"
licence_url: "https://arxiv.org/licenses/nonexclusive-distrib/1.0/license.html"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/chen-2021-spreadsheetcoder-formula-prediction-semi-structured/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/chen-2021-spreadsheetcoder-formula-prediction-semi-structured/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2021](https://md.research.elamur.ai/free/en/papers/2021/page/6/) / SpreadsheetCoder: Formula Prediction from Semi-structured Context

# SpreadsheetCoder: Formula Prediction from Semi-structured Context

**Authors:** [Xinyun Chen](https://md.research.elamur.ai/free/en/authors/xinyun-chen/), Petros Maniatis, [Rishabh Singh](https://md.research.elamur.ai/free/en/authors/rishabh-singh/), [Charles Sutton](https://md.research.elamur.ai/free/en/authors/charles-sutton/), Hanjun Dai, Max Lin and [Denny Zhou](https://md.research.elamur.ai/free/en/authors/denny-zhou/) · **Year:** 2021 · **Venue:** arXiv:2106.15339 · **Licence:** [arXiv — non-exclusive licence to distribute](https://arxiv.org/licenses/nonexclusive-distrib/1.0/license.html)

**Links:** [Publisher's page](https://arxiv.org/abs/2106.15339) · [PDF](https://arxiv.org/pdf/2106.15339v1) · [DOI 10.48550/arxiv.2106.15339](https://doi.org/10.48550/arxiv.2106.15339) · [arXiv 2106.15339](https://arxiv.org/abs/2106.15339) · [OpenAlex](https://openalex.org/W3126805032)

**Citations:** 7 citations (OpenAlex, 2026-10-14) · [24](https://md.research.elamur.ai/free/en/papers/chen-2021-spreadsheetcoder-formula-prediction-semi-structured/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Earlier approaches to spreadsheet formula synthesis, such as FlashFill and its neural successors, treated the problem as programming by example. They treated each row as an independent input-output pair and ignored table headers. This paper argues that real spreadsheets are semi-structured: rows and columns depend on each other, and headers carry useful hints about intent. The authors therefore predict a formula from the surrounding table alone, without an explicit specification.

Their model, SpreadsheetCoder, encodes the context with BERT in two layouts, row-based and column-based, and adds convolutions to capture wider two-dimensional structure. Decoding happens in two stages. The model first produces a formula sketch with placeholders where cell references belong, then fills in those ranges using coordinates relative to the target cell.

On a large corpus of spreadsheets shared publicly inside Google, the model clearly outperforms a programming-by-example baseline. Ablation studies show that both headers and the full data context matter. This makes context-driven formula suggestion practical in a real product, Google Sheets.

## Key points
- Top-1 accuracy is 42.51% for complete formulas and 57.41% for formula sketches, both above neural programming-by-example baselines (Devlin et al., 2017).
- Compared with the existing rule-based system in Google Sheets, SpreadsheetCoder helps 82% more users write formulas.
- The target language is the full Google Sheets formula language, covering about a hundred base functions such as SUM, VLOOKUP, IF and CONCATENATE. This is far broader than the FlashFill DSL.
- Ranges are written relative to the target cell, as R[i] C[j] with offsets bounded by D = 10. Formulas that reference other tabs or use absolute ranges are excluded.
- The paper appeared at ICML 2021 (UC Berkeley and Google). Proposed future directions include spreadsheet-specific pre-training, using formatting cues such as colors and fonts, and applying the approach to bug and clone detection.

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

## Institutions

- [Google](https://md.research.elamur.ai/free/en/companies/google/) — Company, Mountain View, United States · 533 works · 443,885 citations
- [University of California, Berkeley](https://md.research.elamur.ai/free/en/universities/university-of-california-berkeley/) — University, Berkeley, United States · 243 works · 251,774 citations
- [Georgia Institute of Technology](https://md.research.elamur.ai/free/en/universities/georgia-institute-of-technology/) — University, Atlanta, United States · 159 works · 28,096 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 19,503 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,888 works · [💻 Software](https://md.research.elamur.ai/free/en/shelves/computer-science/software/) · 150 works · [🖥️ Computer Science Applications](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-science-applications/) · 184 works

## Cite

Cite as: Xinyun Chen, Petros Maniatis, Rishabh Singh, Charles Sutton, Hanjun Dai, Max Lin and Denny Zhou. 2021. SpreadsheetCoder: Formula Prediction from Semi-structured Context. arXiv:2106.15339.

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

```bibtex
@misc{chen2021spreadsheetcoder,
  title = {{SpreadsheetCoder: Formula Prediction from Semi-structured Context}},
  author = {Xinyun Chen, Petros Maniatis, Rishabh Singh, Charles Sutton, Hanjun Dai, Max Lin and Denny Zhou},
  year = {2021},
  doi = {10.48550/arxiv.2106.15339},
  eprint = {2106.15339},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2106.15339}
}
```

- [← previous Realistic Evaluation Principles for Cross-document Coreference Resolution](https://md.research.elamur.ai/free/en/papers/cattan-2021-realistic-evaluation-principles-cross-document/)
- [next → Evaluating Document Coherence Modeling](https://md.research.elamur.ai/free/en/papers/shen-2021-evaluating-document-coherence-modeling/)
- [↑ back to papers of 2021](https://md.research.elamur.ai/free/en/papers/2021/page/6/)

## References

54 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Azam, A., Alam, K. A., and Umair, A. Spreadsheet smells: A systematic mapping study. In 2019 International Conference on Frontiers of Information Technology (FIT), pp. 345–3455. [find](https://scholar.google.com/scholar?q=Azam%2C+A%2E%2C+Alam%2C+K%2E+A%2E%2C+and+Umair%2C+A%2E+Spreadsheet+smells%3A+A+systematic+mapping+study%2E+In+2019+International+Conference+on+Frontiers+of+Information+Technology+%28FIT%29%2C+pp%2E+345%E2%80%933455%2E)
2. Bahdanau, D., Cho, K., and Bengio, Y. [Neural machine translation by jointly learning to align and translate](https://md.research.elamur.ai/free/en/papers/bahdanau-2014-neural-machine-translation-jointly-learning/). In International Conference on Learning Representations, 2015.
3. Balog, M., Gaunt, A. L., Brockschmidt, M., Nowozin, S., and Tarlow, D. Deepcoder: Learning to write programs. In International Conference on Learning Representations, 2017. [find](https://scholar.google.com/scholar?q=Balog%2C+M%2E%2C+Gaunt%2C+A%2E+L%2E%2C+Brockschmidt%2C+M%2E%2C+Nowozin%2C+S%2E%2C+and+Tarlow%2C+D%2E+Deepcoder%3A+Learning+to+write+programs%2E+In+International+Conference+on+Learning+Representations%2C+2017%2E)
4. Bavishi, R., Lemieux, C., Fox, R., Sen, K., and Stoica, I. Autopandas: neural-backed generators for program synthesis. Proceedings of the ACM on Programming Languages, 3(OOPSLA):1–27, 2019. [find](https://scholar.google.com/scholar?q=Bavishi%2C+R%2E%2C+Lemieux%2C+C%2E%2C+Fox%2C+R%2E%2C+Sen%2C+K%2E%2C+and+Stoica%2C+I%2E+Autopandas%3A+neural%2Dbacked+generators+for+program+synthesis%2E+Proceedings+of+the+ACM+on+Programming+Languages%2C+3%28OOPSLA%29%3A1%E2%80%9327%2C+2019%2E)
5. Bunel, R., Hausknecht, M., Devlin, J., Singh, R., and Kohli, P. [Leveraging grammar and reinforcement learning for neural program synthesis](https://md.research.elamur.ai/free/en/papers/bunel-2018-leveraging-grammar-reinforcement-learning-neural/). In International Conference on Learning Representations, 2018. URL [https://openreview.net/forum?id=H1Xw62kRZ](https://openreview.net/forum?id=H1Xw62kRZ). [↗](https://openreview.net/forum?id=H1Xw62kRZ)
6. Chen, W., Wang, H., Chen, J., Zhang, Y., Wang, H., Li, S., Zhou, X., and Wang, W. Y. [Tabfact: A large-scale dataset for table-based fact verification](https://md.research.elamur.ai/free/en/papers/chen-2019-tabfact-large-scale-dataset-table/). In International Conference on Learning Representations, 2020.
7. Chen, X., Liu, C., and Song, D. Execution-guided neural program synthesis. In International Conference on Learning Representations, 2019. [find](https://scholar.google.com/scholar?q=Chen%2C+X%2E%2C+Liu%2C+C%2E%2C+and+Song%2C+D%2E+Execution%2Dguided+neural+program+synthesis%2E+In+International+Conference+on+Learning+Representations%2C+2019%2E)
8. Cheung, S.-C., Chen, W., Liu, Y., and Xu, C. Custodes: automatic spreadsheet cell clustering and smell detection using strong and weak features. In Proceedings of the 38th International Conference on Software Engineering, pp. 464–475, 2016. [find](https://scholar.google.com/scholar?q=Cheung%2C+S%2E%2DC%2E%2C+Chen%2C+W%2E%2C+Liu%2C+Y%2E%2C+and+Xu%2C+C%2E+Custodes%3A+automatic+spreadsheet+cell+clustering+and+smell+detection+using+strong+and+weak+features%2E+In+Proceedings+of+the+38th+International+Conference+on+)
9. Devlin, J., Uesato, J., Bhupatiraju, S., Singh, R., Mohamed, A., and Kohli, P. Robustfill: Neural program learning under noisy I/O. In ICML, 2017. [find](https://scholar.google.com/scholar?q=Devlin%2C+J%2E%2C+Uesato%2C+J%2E%2C+Bhupatiraju%2C+S%2E%2C+Singh%2C+R%2E%2C+Mohamed%2C+A%2E%2C+and+Kohli%2C+P%2E+Robustfill%3A+Neural+program+learning+under+noisy+I%2FO%2E+In+ICML%2C+2017%2E)
10. Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. [Bert: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In NAACL-HLT (1), 2019.
11. Dong, H., Liu, S., Fu, Z., Han, S., and Zhang, D. Semantic structure extraction for spreadsheet tables with a multi-task learning architecture. In Workshop on Document Intelligence at NeurIPS 2019, 2019a. [find](https://scholar.google.com/scholar?q=Dong%2C+H%2E%2C+Liu%2C+S%2E%2C+Fu%2C+Z%2E%2C+Han%2C+S%2E%2C+and+Zhang%2C+D%2E+Semantic+structure+extraction+for+spreadsheet+tables+with+a+multi%2Dtask+learning+architecture%2E+In+Workshop+on+Document+Intelligence+at+NeurIPS+2019%2C+20)
12. Dong, H., Liu, S., Han, S., Fu, Z., and Zhang, D. [Tablesense: Spreadsheet table detection with convolutional neural networks](https://md.research.elamur.ai/free/en/papers/dong-2021-tablesense-spreadsheet-table-detection-convolutional/). In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pp. 69–76, 2019b.
13. Dong, L. and Lapata, M. Coarse-to-fine decoding for neural semantic parsing. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 731–742, 2018. [find](https://scholar.google.com/scholar?q=Dong%2C+L%2E+and+Lapata%2C+M%2E+Coarse%2Dto%2Dfine+decoding+for+neural+semantic+parsing%2E+In+Proceedings+of+the+56th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+1%3A+Long+Papers%29%2C+pp%2E+731)
14. Dou, W., Cheung, S.-C., Gao, C., Xu, C., Xu, L., and Wei, J. Detecting table clones and smells in spreadsheets. In Proceedings of the 2016 24th ACM SIGSOFT International Symposium on Foundations of Software Engineering, pp. 787–798, 2016. [find](https://scholar.google.com/scholar?q=Dou%2C+W%2E%2C+Cheung%2C+S%2E%2DC%2E%2C+Gao%2C+C%2E%2C+Xu%2C+C%2E%2C+Xu%2C+L%2E%2C+and+Wei%2C+J%2E+Detecting+table+clones+and+smells+in+spreadsheets%2E+In+Proceedings+of+the+2016+24th+ACM+SIGSOFT+International+Symposium+on+Foundations+of+So)
15. Gulwani, S. [Automating string processing in spreadsheets using input-output examples](https://md.research.elamur.ai/free/en/papers/gulwani-2011-automating-string-processing-spreadsheets-input/). In ACM SIGPLAN Notices, volume 46, pp. 317–330. ACM, 2011.
16. Gulwani, S. and Marron, M. Nlyze: Interactive programming by natural language for spreadsheet data analysis and manipulation. In Proceedings of the 2014 ACM SIG-MOD international conference on Management of data, pp. 803–814, 2014. [find](https://scholar.google.com/scholar?q=Gulwani%2C+S%2E+and+Marron%2C+M%2E+Nlyze%3A+Interactive+programming+by+natural+language+for+spreadsheet+data+analysis+and+manipulation%2E+In+Proceedings+of+the+2014+ACM+SIG%2DMOD+international+conference+on+Managem)
17. Gulwani, S., Harris, W. R., and Singh, R. Spreadsheet data manipulation using examples. Communications of the ACM, 55(8):97–105, 2012. [find](https://scholar.google.com/scholar?q=Gulwani%2C+S%2E%2C+Harris%2C+W%2E+R%2E%2C+and+Singh%2C+R%2E+Spreadsheet+data+manipulation+using+examples%2E+Communications+of+the+ACM%2C+55%288%29%3A97%E2%80%93105%2C+2012%2E)
18. Hermans, F. and Murphy-Hill, E. Enron’s spreadsheets and related emails: A dataset and analysis. In 2015 [IEEE/ACM 37th IEEE International Conference on Software Engineering, volume 2, pp](https://md.research.elamur.ai/free/en/papers/hermans-2015-enron-s-spreadsheets-related-emails/). 7–16.
19. Hermans, F., Pinzger, M., and van Deursen, A. Detecting and visualizing inter-worksheet smells in spreadsheets. In 2012 34th International Conference on Software Engineering (ICSE), pp. 441–451. [find](https://scholar.google.com/scholar?q=Hermans%2C+F%2E%2C+Pinzger%2C+M%2E%2C+and+van+Deursen%2C+A%2E+Detecting+and+visualizing+inter%2Dworksheet+smells+in+spreadsheets%2E+In+2012+34th+International+Conference+on+Software+Engineering+%28ICSE%29%2C+pp%2E+441%E2%80%93451%2E)
20. Hermans, F., Pinzger, M., and van Deursen, A. Measuring spreadsheet formula understandability. arXiv preprint arXiv:1209.3517, 2012b. — [arXiv:1209.3517](https://arxiv.org/abs/1209.3517) [find](https://scholar.google.com/scholar?q=Hermans%2C+F%2E%2C+Pinzger%2C+M%2E%2C+and+van+Deursen%2C+A%2E+Measuring+spreadsheet+formula+understandability%2E+arXiv+preprint+arXiv%3A1209%2E3517%2C+2012b%2E+%E2%80%94+%5BarXiv%3A1209%2E3517%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1209%2E3517%29)
21. Hermans, F., Sedee, B., Pinzger, M., and van Deursen, A. Data clone detection and visualization in spreadsheets. In 2013 35th International Conference on Software Engineering (ICSE), pp. 292–301. [find](https://scholar.google.com/scholar?q=Hermans%2C+F%2E%2C+Sedee%2C+B%2E%2C+Pinzger%2C+M%2E%2C+and+van+Deursen%2C+A%2E+Data+clone+detection+and+visualization+in+spreadsheets%2E+In+2013+35th+International+Conference+on+Software+Engineering+%28ICSE%29%2C+pp%2E+292%E2%80%93301%2E)
22. Herzig, J., Nowak, P. K., Müller, T., Piccinno, F., and Eisenschlos, J. M. [Tapas: Weakly supervised table parsing via pre-training](https://md.research.elamur.ai/free/en/papers/herzig-2020-tapas-weakly-supervised-table-parsing/). In Annual Meeting of the Association for Computational Linguistics (ACL), 2020.
23. Hochreiter, S. and Schmidhuber, J. Long short-term memory. Neural computation, 9(8):1735–1780, 1997. [find](https://scholar.google.com/scholar?q=Hochreiter%2C+S%2E+and+Schmidhuber%2C+J%2E+Long+short%2Dterm+memory%2E+Neural+computation%2C+9%288%29%3A1735%E2%80%931780%2C+1997%2E)
24. Iyyer, M., Yih, W.-t., and Chang, M.-W. [Search-based neural structured learning for sequential question answering](https://md.research.elamur.ai/free/en/papers/iyyer-2017-search-based-neural-structured-learning/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1821–1831, 2017.
25. Karpathy, A., Johnson, J., and Fei-Fei, L. [Visualizing and understanding recurrent networks](https://md.research.elamur.ai/free/en/papers/karpathy-2015-visualizing-understanding-recurrent-networks/). arXiv preprint arXiv:1506.02078, 2015.
26. Klimt, B. and Yang, Y. Introducing the enron corpus. In CEAS, 2004. [find](https://scholar.google.com/scholar?q=Klimt%2C+B%2E+and+Yang%2C+Y%2E+Introducing+the+enron+corpus%2E+In+CEAS%2C+2004%2E)
27. Li, J., Wang, Y., Lyu, M. R., and King, I. Code completion with neural attention and pointer networks. In Proceedings of the 27th International Joint Conference on Artificial Intelligence, pp. 4159–25, 2018. [find](https://scholar.google.com/scholar?q=Li%2C+J%2E%2C+Wang%2C+Y%2E%2C+Lyu%2C+M%2E+R%2E%2C+and+King%2C+I%2E+Code+completion+with+neural+attention+and+pointer+networks%2E+In+Proceedings+of+the+27th+International+Joint+Conference+on+Artificial+Intelligence%2C+pp%2E+4159%E2%80%9325)
28. Liang, C., Norouzi, M., Berant, J., Le, Q. V., and Lao, N. Memory augmented policy optimization for program synthesis and semantic parsing. In Advances in Neural Information Processing Systems, pp. 9994–10006, 2018. [find](https://scholar.google.com/scholar?q=Liang%2C+C%2E%2C+Norouzi%2C+M%2E%2C+Berant%2C+J%2E%2C+Le%2C+Q%2E+V%2E%2C+and+Lao%2C+N%2E+Memory+augmented+policy+optimization+for+program+synthesis+and+semantic+parsing%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+pp%2E+99)
29. Lin, X. V., Wang, C., Zettlemoyer, L., and Ernst, M. D. Nl2bash: A corpus and semantic parser for natural language interface to the linux operating system. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), 2018. [find](https://scholar.google.com/scholar?q=Lin%2C+X%2E+V%2E%2C+Wang%2C+C%2E%2C+Zettlemoyer%2C+L%2E%2C+and+Ernst%2C+M%2E+D%2E+Nl2bash%3A+A+corpus+and+semantic+parser+for+natural+language+interface+to+the+linux+operating+system%2E+In+Proceedings+of+the+Eleventh+International)
30. Liu, Y. and Wu, Z. Learning to describe scenes with programs. In International Conference on Learning Representations, 2019. [find](https://scholar.google.com/scholar?q=Liu%2C+Y%2E+and+Wu%2C+Z%2E+Learning+to+describe+scenes+with+programs%2E+In+International+Conference+on+Learning+Representations%2C+2019%2E)
31. Murali, V., Qi, L., Chaudhuri, S., and Jermaine, C. Neural sketch learning for conditional program generation. In International Conference on Learning Representations, 2018. [find](https://scholar.google.com/scholar?q=Murali%2C+V%2E%2C+Qi%2C+L%2E%2C+Chaudhuri%2C+S%2E%2C+and+Jermaine%2C+C%2E+Neural+sketch+learning+for+conditional+program+generation%2E+In+International+Conference+on+Learning+Representations%2C+2018%2E)
32. Nye, M., Hewitt, L., Tenenbaum, J., and Solar-Lezama, A. [Learning to infer program sketches](https://md.research.elamur.ai/free/en/papers/nye-2019-learning-infer-program-sketches/). In International Conference on Machine Learning, pp. 4861–4870, 2019.
33. Odena, A., Shi, K., Bieber, D., Singh, R., and Sutton, C. Bustle: Bottom-up program-synthesis through learning-guided exploration. arXiv preprint arXiv:2007.14381, 2020. [find](https://scholar.google.com/scholar?q=Odena%2C+A%2E%2C+Shi%2C+K%2E%2C+Bieber%2C+D%2E%2C+Singh%2C+R%2E%2C+and+Sutton%2C+C%2E+Bustle%3A+Bottom%2Dup+program%2Dsynthesis+through+learning%2Dguided+exploration%2E+arXiv+preprint+arXiv%3A2007%2E14381%2C+2020%2E)
34. Parisotto, E., Mohamed, A.-r., Singh, R., Li, L., Zhou, D., and Kohli, P. [Neuro-symbolic program synthesis](https://md.research.elamur.ai/free/en/papers/parisotto-2016-neuro-symbolic-program-synthesis/). In International Conference on Learning Representations, 2017.
35. Polozov, O. and Gulwani, S. Flashmeta: a framework for inductive program synthesis. In Proceedings of the 2015 ACM SIGPLAN International Conference on Object-Oriented Programming, Systems, Languages, and Applications, pp. 107–126, 2015. [find](https://scholar.google.com/scholar?q=Polozov%2C+O%2E+and+Gulwani%2C+S%2E+Flashmeta%3A+a+framework+for+inductive+program+synthesis%2E+In+Proceedings+of+the+2015+ACM+SIGPLAN+International+Conference+on+Object%2DOriented+Programming%2C+Systems%2C+Languages%2C+)
36. Popescu, A.-M., Etzioni, O., and Kautz, H. Towards a theory of natural language interfaces to databases. In Proceedings of the 8th international conference on Intelligent user interfaces, pp. 149–157, 2003. [find](https://scholar.google.com/scholar?q=Popescu%2C+A%2E%2DM%2E%2C+Etzioni%2C+O%2E%2C+and+Kautz%2C+H%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+149%E2%80%93157%2C)
37. Raychev, V., Vechev, M., and Yahav, E. Code completion with statistical language models. In Proceedings of the 35th ACM SIGPLAN Conference on Programming Language Design and Implementation, pp. 419–428, 2014. [find](https://scholar.google.com/scholar?q=Raychev%2C+V%2E%2C+Vechev%2C+M%2E%2C+and+Yahav%2C+E%2E+Code+completion+with+statistical+language+models%2E+In+Proceedings+of+the+35th+ACM+SIGPLAN+Conference+on+Programming+Language+Design+and+Implementation%2C+pp%2E+419%E2%80%9342)
38. Shin, E. C., Polosukhin, I., and Song, D. Improving neural program synthesis with inferred execution traces. In Advances in Neural Information Processing Systems, pp. 8917–8926, 2018. [find](https://scholar.google.com/scholar?q=Shin%2C+E%2E+C%2E%2C+Polosukhin%2C+I%2E%2C+and+Song%2C+D%2E+Improving+neural+program+synthesis+with+inferred+execution+traces%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+pp%2E+8917%E2%80%938926%2C+2018%2E)
39. Singh, R., Livshits, B., and Zorn, B. Melford: Using neural networks to find spreadsheet errors. 2017. [find](https://scholar.google.com/scholar?q=Singh%2C+R%2E%2C+Livshits%2C+B%2E%2C+and+Zorn%2C+B%2E+Melford%3A+Using+neural+networks+to+find+spreadsheet+errors%2E+2017%2E)
40. Solar-Lezama, A. [Program Synthesis by Sketching](https://md.research.elamur.ai/free/en/papers/lezama-2008-program-synthesis-sketching/). PhD thesis, UNIVERSITY OF CALIFORNIA, BERKELEY, 2008.
41. Sun, S.-H., Noh, H., Somasundaram, S., and Lim, J. Neural program synthesis from diverse demonstration videos. In International Conference on Machine Learning, pp. 4790–4799, 2018. [find](https://scholar.google.com/scholar?q=Sun%2C+S%2E%2DH%2E%2C+Noh%2C+H%2E%2C+Somasundaram%2C+S%2E%2C+and+Lim%2C+J%2E+Neural+program+synthesis+from+diverse+demonstration+videos%2E+In+International+Conference+on+Machine+Learning%2C+pp%2E+4790%E2%80%934799%2C+2018%2E)
42. Sundermeyer, M., Schlüter, R., and Ney, H. Lstm neural networks for language modeling. In Thirteenth annual conference of the international speech communication association, 2012. [find](https://scholar.google.com/scholar?q=Sundermeyer%2C+M%2E%2C+Schlu%CC%88ter%2C+R%2E%2C+and+Ney%2C+H%2E+Lstm+neural+networks+for+language+modeling%2E+In+Thirteenth+annual+conference+of+the+international+speech+communication+association%2C+2012%2E)
43. Svyatkovskiy, A., Zhao, Y., Fu, S., and Sundaresan, N. Pythia: AI-assisted code completion system. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2727–2735, 2019. [find](https://scholar.google.com/scholar?q=Svyatkovskiy%2C+A%2E%2C+Zhao%2C+Y%2E%2C+Fu%2C+S%2E%2C+and+Sundaresan%2C+N%2E+Pythia%3A+AI%2Dassisted+code+completion+system%2E+In+Proceedings+of+the+25th+ACM+SIGKDD+International+Conference+on+Knowledge+Discovery+%26+Data+Mining%2C+)
44. Svyatkovskiy, A., Deng, S. K., Fu, S., and Sundaresan, N. Intellicode compose: Code generation using transformer. arXiv preprint arXiv:2005.08025, 2020. [find](https://scholar.google.com/scholar?q=Svyatkovskiy%2C+A%2E%2C+Deng%2C+S%2E+K%2E%2C+Fu%2C+S%2E%2C+and+Sundaresan%2C+N%2E+Intellicode+compose%3A+Code+generation+using+transformer%2E+arXiv+preprint+arXiv%3A2005%2E08025%2C+2020%2E)
45. Svyatkovskoy, A., Lee, S., Hadjitofi, A., Riechert, M., Franco, J., and Allamanis, M. Fast and memory-efficient neural code completion. arXiv preprint arXiv:2004.13651, 2020. — [arXiv:2004.13651](https://arxiv.org/abs/2004.13651) [find](https://scholar.google.com/scholar?q=Svyatkovskoy%2C+A%2E%2C+Lee%2C+S%2E%2C+Hadjitofi%2C+A%2E%2C+Riechert%2C+M%2E%2C+Franco%2C+J%2E%2C+and+Allamanis%2C+M%2E+Fast+and+memory%2Defficient+neural+code+completion%2E+arXiv+preprint+arXiv%3A2004%2E13651%2C+2020%2E+%E2%80%94+%5BarXiv%3A2004%2E13651%5D%28http)
46. Vijayakumar, A. J., Mohta, A., Polozov, O., Batra, D., Jain, P., and Gulwani, S. Neural-guided deductive search for real-time program synthesis from examples. In ICLR, 2018. [find](https://scholar.google.com/scholar?q=Vijayakumar%2C+A%2E+J%2E%2C+Mohta%2C+A%2E%2C+Polozov%2C+O%2E%2C+Batra%2C+D%2E%2C+Jain%2C+P%2E%2C+and+Gulwani%2C+S%2E+Neural%2Dguided+deductive+search+for+real%2Dtime+program+synthesis+from+examples%2E+In+ICLR%2C+2018%2E)
47. Wang, B., Shin, R., Liu, X., Polozov, O., and Richardson, M. [Rat-sql: Relation-aware schema encoding and linking for text-to-sql parsers](https://md.research.elamur.ai/free/en/papers/wang-2020-rat-sql-relation-aware-schema/). In Annual Meeting of the Association for Computational Linguistics (ACL), 2020.
48. Wu, J., Tenenbaum, J. B., and Kohli, P. Neural scene derendering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 699–707, 2017. [find](https://scholar.google.com/scholar?q=Wu%2C+J%2E%2C+Tenenbaum%2C+J%2E+B%2E%2C+and+Kohli%2C+P%2E+Neural+scene+derendering%2E+In+Proceedings+of+the+IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition%2C+pp%2E+699%E2%80%93707%2C+2017%2E)
49. Yin, P., Deng, B., Chen, E., Vasilescu, B., and Neubig, G. [Learning to mine aligned code and natural language pairs from stack overflow](https://md.research.elamur.ai/free/en/papers/yin-2018-learning-mine-aligned-code-natural/). In 2018 IEEE/ACM 15th International Conference on Mining Software Repositories (MSR), pp. 476–486.
50. Yin, P., Neubig, G., Yih, W.-t., and Riedel, S. Tabert: Pre-training for joint understanding of textual and tabular data. In Annual Meeting of the Association for Computational Linguistics (ACL), 2020. [find](https://scholar.google.com/scholar?q=Yin%2C+P%2E%2C+Neubig%2C+G%2E%2C+Yih%2C+W%2E%2Dt%2E%2C+and+Riedel%2C+S%2E+Tabert%3A+Pre%2Dtraining+for+joint+understanding+of+textual+and+tabular+data%2E+In+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28ACL%29%2C+2020)
51. Yu, T., Zhang, R., Yang, K., Yasunaga, M., Wang, D., Li, Z., Ma, J., Li, I., Yao, Q., Roman, S., et al. [Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task](https://md.research.elamur.ai/free/en/papers/yu-2018-spider-large-scale-human-labeled/). In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Proce…
52. Zhang, Y., Dou, W., Zhu, J., Xu, L., Zhou, Z., Wei, J., Ye, D., and Yang, B. Learning to detect table clones in spreadsheets. In Proceedings of the 29th ACM SIG-SOFT International Symposium on Software Testing and Analysis, pp. 528–540, 2020. [find](https://scholar.google.com/scholar?q=Zhang%2C+Y%2E%2C+Dou%2C+W%2E%2C+Zhu%2C+J%2E%2C+Xu%2C+L%2E%2C+Zhou%2C+Z%2E%2C+Wei%2C+J%2E%2C+Ye%2C+D%2E%2C+and+Yang%2C+B%2E+Learning+to+detect+table+clones+in+spreadsheets%2E+In+Proceedings+of+the+29th+ACM+SIG%2DSOFT+International+Symposium+on+Softwar)
53. Zhong, V., Xiong, C., and Socher, R. [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.
54. Figure 8. Top-1 formula accuracies for different sketch lengths, excluding headers in the context. A. An Extended Discussion of Related Work [find](https://scholar.google.com/scholar?q=Figure+8%2E+Top%2D1+formula+accuracies+for+different+sketch+lengths%2C+excluding+headers+in+the+context%2E+A%2E+An+Extended+Discussion+of+Related+Work)

*Updated 3 November 2026*