---
title: "MTO — paper by Zhang et al. (2026) — summary and ideas"
description: "The authors build MTO, which they describe as the first conversational benchmark for this task, by extending… 67.4 chrF. 30 references."
authors: ["Haodi Zhang", "Xinrui Zhu", "Mingze Kong", "Zhidan Liu", "Tao Fan", "Kaishun Wu", "Yuanfeng Song"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.36/"
doi: "10.18653/v1/2026.findings-acl.36"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhang-2026-mto-multi-turn-conversational-text/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2026-mto-multi-turn-conversational-text/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/42/) / MTO: A Multi-turn Conversational Text-to-OverpassQL Dataset for Enhanced OpenStreetMap Query Generation

# MTO: A Multi-turn Conversational Text-to-OverpassQL Dataset for Enhanced OpenStreetMap Query Generation

**Authors:** Haodi Zhang, Xinrui Zhu, Mingze Kong, Zhidan Liu, [Tao Fan](https://md.research.elamur.ai/free/en/authors/tao-fan/), [Kaishun Wu](https://md.research.elamur.ai/free/en/authors/kaishun-wu/) and [Yuanfeng Song](https://md.research.elamur.ai/free/en/authors/yuanfeng-song/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.36/) · [PDF](https://aclanthology.org/2026.findings-acl.36.pdf) · [DOI 10.18653/v1/2026.findings-acl.36](https://doi.org/10.18653/v1/2026.findings-acl.36) · [OpenAlex](https://openalex.org/W7166801632)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
OverpassQL, the query language for OpenStreetMap (OSM), is hard for non-experts to learn. Earlier text-to-OverpassQL resources such as OverpassNL handle only single, isolated questions, while real users usually refine a request over several turns. The authors build MTO, which they describe as the first conversational benchmark for this task, by extending OverpassNL with a four-step pipeline:

1. A custom parser based on the official grammar converts each query into a syntax tree.
2. Tree-editing templates alter the tree, from small keyword swaps to larger structural splits, producing related queries that remain executable.
3. Prompted LLMs write natural-language turns whose dependence on earlier context grows over the dialogue.
4. Manual checks combined with model-assisted filtering confirm that questions and queries match.

The authors tested several commercial and open LLMs alongside a fine-tuned ByT5-Large. The fine-tuned model led on every similarity metric and on soft execution. On strict execution accuracy it was roughly level with the best LLMs. The resource supports research on context-aware semantic parsing for geospatial data.

## Key points
- **Dataset size:** The paper gives slightly different figures for the size of MTO. The abstract reports more than 7,800 dialogues and over 20,000 utterances. The introduction reports 7,878 dialogues and 21,501 utterance–query pairs. Each dialogue has 2–4 user turns.
- **Source corpus:** The source is OverpassNL (Staniek et al., 2024), which contains about 8.5k single-turn pairs. Region placeholders in MTO are resolved using the latitude–longitude bounds from the original instances.
- **ByT5-Large results:** The fine-tuned ByT5-Large reached 59.0 KVS, 65.4 TreeS, 67.4 chrF and 64.0 OQS. Its soft execution accuracy was 25.0, and its execution accuracy was 15.9, compared with 15.1 for GPT-4.1mini and 16.0 for DeepSeek V3.1.
- **Other models evaluated:** The benchmark also covered Qwen3-235b and Gemini 2.5-Flash, both using standard, unconstrained prompting.
- **Limitations:**
  - The pipeline depends on grammars and templates written for one specific domain.
  - Validation is done in batches rather than per dialogue.
  - When tested on OverpassNL, the MTO-trained ByT5 transfers only moderately (chrF 55.34, EX 14.1). It does worse than a ByT5 model trained directly on OverpassNL.

*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

- [Hong Kong University of Science and Technology](https://md.research.elamur.ai/free/en/universities/hong-kong-university-of-science-and-technology/) — University, Hong Kong, China · 170 works · 26,341 citations
- [Chinese University of Hong Kong, Shenzhen](https://md.research.elamur.ai/free/en/universities/chinese-university-of-hong-kong-shenzhen/) — University, Shenzhen, China · 56 works · 3,212 citations
- [The Hong Kong University of Science and Technology (Guangzhou)](https://md.research.elamur.ai/free/en/universities/the-hong-kong-university-of-science-and-technology-guangzhou/) — University, Guangzhou, China · 67 works · 1,765 citations
- [Shenzhen University](https://md.research.elamur.ai/free/en/universities/shenzhen-university/) — University, Shenzhen, China · 22 works · 95 citations

📚 Shelves (4): [🖥️ 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

🧭 Topics (1): [🗨️ Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · 654 works

## Cite

Cite as: Haodi Zhang, Xinrui Zhu, Mingze Kong, Zhidan Liu, Tao Fan, Kaishun Wu and Yuanfeng Song. 2026. MTO: A Multi-turn Conversational Text-to-OverpassQL Dataset for Enhanced OpenStreetMap Query Generation. Findings of the Association for Computational Linguistics: ACL 2026.

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

```bibtex
@inproceedings{zhang2026mto,
  title = {{MTO: A Multi-turn Conversational Text-to-OverpassQL Dataset for Enhanced OpenStreetMap Query Generation}},
  author = {Haodi Zhang, Xinrui Zhu, Mingze Kong, Zhidan Liu, Tao Fan, Kaishun Wu and Yuanfeng Song},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.36},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.36}
}
```

- [← previous MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues](https://md.research.elamur.ai/free/en/papers/pan-2026-mt-video-bench-holistic-video/)
- [next → MTP-RL: Acceleration of Reinforcement Learning Rollouts with Policy-Aligned Multi-Token Prediction](https://md.research.elamur.ai/free/en/papers/wang-2026-mtp-rl-acceleration-reinforcement-learning/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/42/)

## References

30 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Maciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger, Michal Podstawski, Lukas Gianinazzi, Joanna Gajda, Tomasz Lehmann, Hubert Niewiadomski, Piotr Nyczyk, and 1 others. 2024. Graph of thoughts: Solving elaborate problems with large language models. In Proceedings of the AAAI Conference on A… [find](https://scholar.google.com/scholar?q=Maciej+Besta%2C+Nils+Blach%2C+Ales+Kubicek%2C+Robert+Gerstenberger%2C+Michal+Podstawski%2C+Lukas+Gianinazzi%2C+Joanna+Gajda%2C+Tomasz+Lehmann%2C+Hubert+Niewiadomski%2C+Piotr+Nyczyk%2C+and+1+others%2E+2024%2E+Graph+of+thought)
2. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, and… [find](https://scholar.google.com/scholar?q=Tom+Brown%2C+Benjamin+Mann%2C+Nick+Ryder%2C+Melanie+Subbiah%2C+Jared+D+Kaplan%2C+Prafulla+Dhariwal%2C+Arvind+Neelakantan%2C+Pranav+Shyam%2C+Girish+Sastry%2C+Amanda+Askell%2C+Sandhini+Agarwal%2C+Ariel+Herbert%2DVoss%2C+Gretchen)
3. Paweł Budzianowski, Tsung-Hsien Wen, Bo-Hsiang Tseng, Iñigo Casanueva, Stefan Ultes, Osman Ramadan, and Milica Gašić. 2018. [MultiWOZ - a large-scale multi-domain Wizard-of-Oz dataset for task-oriented dialogue modelling](https://md.research.elamur.ai/free/en/papers/budzianowski-2018-multiwoz-large-scale-multi-domain/). In Proceedings of the 2018 Conference on Empirical Methods in Natural Language…
4. Jan Deriu, Katsiaryna Mlynchyk, Philippe Schlapfer, Álvaro Rodrigo, Dirk von Grunigen, Nicolas Kaiser, Kurt Stockinger, Eneko Agirre, and Mark Cieliebak. 2020. A methodology for creating question answering corpora using inverse data annotation. In Annual Meeting of the Association for Computational… [find](https://scholar.google.com/scholar?q=Jan+Deriu%2C+Katsiaryna+Mlynchyk%2C+Philippe+Schlapfer%2C+%C3%81lvaro+Rodrigo%2C+Dirk+von+Grunigen%2C+Nicolas+Kaiser%2C+Kurt+Stockinger%2C+Eneko+Agirre%2C+and+Mark+Cieliebak%2E+2020%2E+A+methodology+for+creating+question+answ)
5. Mingwen Dong, Nischal Ashok Kumar, Yiqun Hu, Anuj Chauhan, Chung-Wei Hang, Shuaichen Chang, Lin Pan, Wuwei Lan, Henghui Zhu, Jiarong Jiang, Patrick Ng, and Zhiguo Wang. 2025. [PRACTIQ: A practical conversational text-to-SQL dataset with ambiguous and unanswerable queries](https://md.research.elamur.ai/free/en/papers/dong-2025-practiq-practical-conversational-text-sql/). In Proceedings of the 2025 C…
6. Jiaqi Guo, Ziliang Si, Yu Wang, Qian Liu, Ming Fan, Jian-Guang Lou, Zijiang Yang, and Ting Liu. 2021. Chase: A large-scale and pragmatic Chinese dataset for cross-database context-dependent text-to-SQL. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and th… [find](https://scholar.google.com/scholar?q=Jiaqi+Guo%2C+Ziliang+Si%2C+Yu+Wang%2C+Qian+Liu%2C+Ming+Fan%2C+Jian%2DGuang+Lou%2C+Zijiang+Yang%2C+and+Ting+Liu%2E+2021%2E+Chase%3A+A+large%2Dscale+and+pragmatic+Chinese+dataset+for+cross%2Ddatabase+context%2Ddependent+text%2Dto%2DSQ)
7. Charles T. Hemphill, John J. Godfrey, and George R. Doddington. 1990. The ATIS spoken language systems pilot corpus. In Speech and Natural Language: Proceedings of a Workshop Held at Hidden Valley, Pennsylvania, June 24-27,1990. [find](https://scholar.google.com/scholar?q=Charles+T%2E+Hemphill%2C+John+J%2E+Godfrey%2C+and+George+R%2E+Doddington%2E+1990%2E+The+ATIS+spoken+language+systems+pilot+corpus%2E+In+Speech+and+Natural+Language%3A+Proceedings+of+a+Workshop+Held+at+Hidden+Valley%2C+Pe)
8. Matthew Henderson, Blaise Thomson, and Jason D. Williams. 2014. The second dialog state tracking challenge. In Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pages 263–272, Philadelphia, PA, U.S.A. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Matthew+Henderson%2C+Blaise+Thomson%2C+and+Jason+D%2E+Williams%2E+2014%2E+The+second+dialog+state+tracking+challenge%2E+In+Proceedings+of+the+15th+Annual+Meeting+of+the+Special+Interest+Group+on+Discourse+and+Dia)
9. Carolin Lawrence and Stefan Riezler. 2016. NLmaps: A natural language interface to query OpenStreetMap. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations, pages 6–10, Osaka, Japan. [find](https://scholar.google.com/scholar?q=Carolin+Lawrence+and+Stefan+Riezler%2E+2016%2E+NLmaps%3A+A+natural+language+interface+to+query+OpenStreetMap%2E+In+Proceedings+of+COLING+2016%2C+the+26th+International+Conference+on+Computational+Linguistics%3A+S)
10. The COLING 2016 Organizing Committee. [find](https://scholar.google.com/scholar?q=The+COLING+2016+Organizing+Committee%2E)
11. Lei Li, Yuqi Wang, Runxin Xu, Peiyi Wang, Xiachong Feng, Lingpeng Kong, and Qi Liu. 2024. [Multimodal ArXiv: A dataset for improving scientific comprehension of large vision-language models](https://md.research.elamur.ai/free/en/papers/li-2024-multimodal-arxiv-dataset-improving-scientific/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pap…
12. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, and 1 others. 2022. [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). Advances in neural information processing systems, 35:27730–27744.
13. Zhiyang Qi, Takumasa Kaneko, Keiko Takamizo, Mariko Ukiyo, and Michimasa Inaba. 2025. Kokorochat: A japanese psychological counseling dialogue dataset collected via role-playing by trained counselors. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume… [find](https://scholar.google.com/scholar?q=Zhiyang+Qi%2C+Takumasa+Kaneko%2C+Keiko+Takamizo%2C+Mariko+Ukiyo%2C+and+Michimasa+Inaba%2E+2025%2E+Kokorochat%3A+A+japanese+psychological+counseling+dialogue+dataset+collected+via+role%2Dplaying+by+trained+counselors%2E)
14. Ge Qu, Jinyang Li, Bowen Li, Bowen Qin, Nan Huo, Chenhao Ma, and Reynold Cheng. 2024. Before generation, align it! a novel and effective strategy for mitigating hallucinations in text-to-SQL generation. In Findings of the Association for Computational Linguistics ACL 2024. Association for Computatio… [find](https://scholar.google.com/scholar?q=Ge+Qu%2C+Jinyang+Li%2C+Bowen+Li%2C+Bowen+Qin%2C+Nan+Huo%2C+Chenhao+Ma%2C+and+Reynold+Cheng%2E+2024%2E+Before+generation%2C+align+it%21+a+novel+and+effective+strategy+for+mitigating+hallucinations+in+text%2Dto%2DSQL+generatio)
15. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. [Exploring the limits of transfer learning with a unified text-to-text transformer](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). J. Mach. Learn. Res., 21(1).
16. Tonghui Ren, Yuankai Fan, Zhenying He, Ren Huang, Jiaqi Dai, Can Huang, Yinan Jing, Kai Zhang, Yifan Yang, and Xiaoyang Sean Wang. 2024. Purple: Making a large language model a better sql writer. 2024 IEEE 40th International Conference on Data Engineering (ICDE), pages 15–28. [find](https://scholar.google.com/scholar?q=Tonghui+Ren%2C+Yuankai+Fan%2C+Zhenying+He%2C+Ren+Huang%2C+Jiaqi+Dai%2C+Can+Huang%2C+Yinan+Jing%2C+Kai+Zhang%2C+Yifan+Yang%2C+and+Xiaoyang+Sean+Wang%2E+2024%2E+Purple%3A+Making+a+large+language+model+a+better+sql+writer%2E+2024)
17. Jaehee Ryu, Seonhee Cho, Gyubok Lee, and Edward Choi. 2024. EHR-SeqSQL : A sequential text-to-SQL dataset for interactively exploring electronic health records. In Findings of the Association for Computational Linguistics: ACL 2024, pages 16388– 16407, Bangkok, Thailand. Association for Computationa… [find](https://scholar.google.com/scholar?q=Jaehee+Ryu%2C+Seonhee+Cho%2C+Gyubok+Lee%2C+and+Edward+Choi%2E+2024%2E+EHR%2DSeqSQL+%3A+A+sequential+text%2Dto%2DSQL+dataset+for+interactively+exploring+electronic+health+records%2E+In+Findings+of+the+Association+for+Comp)
18. Torsten Scholak, Nathan Schucher, and Dzmitry Bahdanau. 2021. PICARD: Parsing incrementally for constrained auto-regressive decoding from language models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9895–9901, Online and Punta Cana, Dominican Repu… [find](https://scholar.google.com/scholar?q=Torsten+Scholak%2C+Nathan+Schucher%2C+and+Dzmitry+Bahdanau%2E+2021%2E+PICARD%3A+Parsing+incrementally+for+constrained+auto%2Dregressive+decoding+from+language+models%2E+In+Proceedings+of+the+2021+Conference+on+Empi)
19. Semantic Machines, Jacob Andreas, John Bufe, David Burkett, Charles Chen, Josh Clausman, Jean Crawford, Kate Crim, Jordan DeLoach, Leah Dorner, Jason Eisner, Hao Fang, Alan Guo, David Hall, Kristin Hayes, Kellie Hill, Diana Ho, Wendy Iwaszuk, Smriti Jha, and 27 others. 2020. [Task-oriented dialogue a…](https://md.research.elamur.ai/free/en/papers/andreas-2020-task-oriented-dialogue-as-dataflow/)
20. Michael Staniek, Raphael Schumann, Maike Züfle, and Stefan Riezler. 2024. Text-to-overpassql: A natural language interface for complex geodata querying of openstreetmap. Transactions of the Association for Computational Linguistics, 12:562–575. [find](https://scholar.google.com/scholar?q=Michael+Staniek%2C+Raphael+Schumann%2C+Maike+Z%C3%BCfle%2C+and+Stefan+Riezler%2E+2024%2E+Text%2Dto%2Doverpassql%3A+A+natural+language+interface+for+complex+geodata+querying+of+openstreetmap%2E+Transactions+of+the+Associatio)
21. Wen tau Yih, Matthew Richardson, Christopher Meek, Ming-Wei Chang, and Jina Suh. 2016. [The value of semantic parse labeling for knowledge base question answering](https://md.research.elamur.ai/free/en/papers/yih-2016-value-semantic-parse-labeling-knowledge/). In Annual Meeting of the Association for Computational Linguistics.
22. Priyansh Trivedi, Gaurav Maheshwari, Mohnish Dubey, and Jens Lehmann. 2017. Lc-quad: A corpus for complex question answering over knowledge graphs. In International Semantic Web Conference, pages 210–218. Springer. [find](https://scholar.google.com/scholar?q=Priyansh+Trivedi%2C+Gaurav+Maheshwari%2C+Mohnish+Dubey%2C+and+Jens+Lehmann%2E+2017%2E+Lc%2Dquad%3A+A+corpus+for+complex+question+answering+over+knowledge+graphs%2E+In+International+Semantic+Web+Conference%2C+pages+210%E2%80%93)
23. Zhuoyue Wan, Wentao Hu, Chen Jason Zhang, Yuanfeng Song, Shuaimin Li, Ruiqiang Xiao, Xiao-Yong Wei, and Raymond Chi-Wing Wong. 2026. Osmt: Bridging openstreetmap queries and natural language with open-source tag-aware language models. In 2026 IEEE 42nd International Conference on Data Engineering (I… [find](https://scholar.google.com/scholar?q=Zhuoyue+Wan%2C+Wentao+Hu%2C+Chen+Jason+Zhang%2C+Yuanfeng+Song%2C+Shuaimin+Li%2C+Ruiqiang+Xiao%2C+Xiao%2DYong+Wei%2C+and+Raymond+Chi%2DWing+Wong%2E+2026%2E+Osmt%3A+Bridging+openstreetmap+queries+and+natural+language+with+open)
24. Xiangjin Xie, Guangwei Xu, Lingyan Zhao, and Ruijie Guo. 2025. Opensearch-sql: Enhancing text-to-sql with dynamic few-shot and consistency alignment. Proc. ACM Manag. Data, 3(3). [find](https://scholar.google.com/scholar?q=Xiangjin+Xie%2C+Guangwei+Xu%2C+Lingyan+Zhao%2C+and+Ruijie+Guo%2E+2025%2E+Opensearch%2Dsql%3A+Enhancing+text%2Dto%2Dsql+with+dynamic+few%2Dshot+and+consistency+alignment%2E+Proc%2E+ACM+Manag%2E+Data%2C+3%283%29%2E)
25. Jiaxi Yang, Binyuan Hui, Min Yang, Jian Yang, Junyang Lin, and Chang Zhou. 2024. Synthesizing text-to-SQL data from weak and strong LLMs. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jiaxi+Yang%2C+Binyuan+Hui%2C+Min+Yang%2C+Jian+Yang%2C+Junyang+Lin%2C+and+Chang+Zhou%2E+2024%2E+Synthesizing+text%2Dto%2DSQL+data+from+weak+and+strong+LLMs%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+Association+f)
26. Tao Yu, Rui Zhang, Heyang Er, Suyi Li, Eric Xue, Bo Pang, Xi Victoria Lin, Yi Chern Tan, Tianze Shi, Zihan Li, Youxuan Jiang, Michihiro Yasunaga, Sungrok Shim, Tao Chen, Alexander Fabbri, Zifan Li, Luyao Chen, Yuwen Zhang, Shreya Dixit, and 5 others. 2019a. CoSQL: A conversational text-to-SQL challe… [find](https://scholar.google.com/scholar?q=Tao+Yu%2C+Rui+Zhang%2C+Heyang+Er%2C+Suyi+Li%2C+Eric+Xue%2C+Bo+Pang%2C+Xi+Victoria+Lin%2C+Yi+Chern+Tan%2C+Tianze+Shi%2C+Zihan+Li%2C+Youxuan+Jiang%2C+Michihiro+Yasunaga%2C+Sungrok+Shim%2C+Tao+Chen%2C+Alexander+Fabbri%2C+Zifan+Li%2C+Lu)
27. Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, Zilin Zhang, and Dragomir Radev. 2018. [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…
28. Tao Yu, Rui Zhang, Michihiro Yasunaga, Yi Chern Tan, Xi Victoria Lin, Suyi Li, Heyang Er, Irene Li, Bo Pang, Tao Chen, Emily Ji, Shreya Dixit, David Proctor, Sungrok Shim, Jonathan Kraft, Vincent Zhang, Caiming Xiong, Richard Socher, and Dragomir Radev. 2019b. [SParC: Cross-domain semantic parsing in…](https://md.research.elamur.ai/free/en/papers/yu-2019-sparc-cross-domain-semantic-parsing/)
29. Haodi Zhang, Xinrui Zhu, Xuan Wang, Yuanfeng Song, Hanlin Gu, and Lin Ma. 2025. Natural language to overpass query: A multi-step approach using task decomposition and key-value correction. In 2025 26th IEEE International Conference on Mobile Data Management (MDM), pages 1–11. [find](https://scholar.google.com/scholar?q=Haodi+Zhang%2C+Xinrui+Zhu%2C+Xuan+Wang%2C+Yuanfeng+Song%2C+Hanlin+Gu%2C+and+Lin+Ma%2E+2025%2E+Natural+language+to+overpass+query%3A+A+multi%2Dstep+approach+using+task+decomposition+and+key%2Dvalue+correction%2E+In+2025+26t)
30. Victor Zhong, Caiming Xiong, and Richard Socher. 2017. [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/). CoRR, abs/1709.00103.

*Updated 2 November 2026*