@inproceedings{zhang-etal-2026-mto,
title = "{MTO}: A Multi-turn Conversational Text-to-{O}verpass{QL} Dataset for Enhanced {O}pen{S}treet{M}ap Query Generation",
author = "Zhang, Haodi and
Zhu, Xinrui and
Kong, Mingze and
Liu, Zhidan and
Fan, Tao and
Wu, Kaishun and
Song, Yuanfeng",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.36/",
pages = "750--771",
ISBN = "979-8-89176-395-1",
abstract = "We propose a comprehensive framework for constructing multi-turn Text-to-OverpassQL dialogue datasets. Under this framework, we introduce the first multi-turn Text-to-OverpassQL dataset built upon the OverpassNL corpus. Our dataset comprises over 7,800 dialogues, each containing 2 to 4 user utterances, resulting in more than 20,000 individual utterances aligned with executable Overpass queries. To generate high-quality multi-turn dialogues, we design a four-stage pipeline. First, we convert Overpass queries into syntax trees using a custom parser developed based on the official OverpassQL grammar. This enables structural manipulation while preserving syntactic and executable validity. Second, we apply a diverse set of tree-editing templates, including both simple keyword-level changes and complex structural decompositions, to produce multiple valid and diverse Overpass queries. Third, we leverage a prompt-based approach to guide large language models in generating context-aware natural language questions, ensuring increasing inter-turn dependency across the dialogue. Finally, we implement a hybrid filtering strategy that combines manual annotation with model-assisted selection to validate alignment and correctness at scale. In addition to presenting the dataset, we evaluate the performance of several mainstream large language models and demonstrate that our end-to-end baseline model achieves competitive results. This work offers a new benchmark for studying executable semantic parsing and contextual understanding in map-based query tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-mto">
<titleInfo>
<title>MTO: A Multi-turn Conversational Text-to-OverpassQL Dataset for Enhanced OpenStreetMap Query Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haodi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinrui</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingze</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhidan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaishun</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanfeng</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>We propose a comprehensive framework for constructing multi-turn Text-to-OverpassQL dialogue datasets. Under this framework, we introduce the first multi-turn Text-to-OverpassQL dataset built upon the OverpassNL corpus. Our dataset comprises over 7,800 dialogues, each containing 2 to 4 user utterances, resulting in more than 20,000 individual utterances aligned with executable Overpass queries. To generate high-quality multi-turn dialogues, we design a four-stage pipeline. First, we convert Overpass queries into syntax trees using a custom parser developed based on the official OverpassQL grammar. This enables structural manipulation while preserving syntactic and executable validity. Second, we apply a diverse set of tree-editing templates, including both simple keyword-level changes and complex structural decompositions, to produce multiple valid and diverse Overpass queries. Third, we leverage a prompt-based approach to guide large language models in generating context-aware natural language questions, ensuring increasing inter-turn dependency across the dialogue. Finally, we implement a hybrid filtering strategy that combines manual annotation with model-assisted selection to validate alignment and correctness at scale. In addition to presenting the dataset, we evaluate the performance of several mainstream large language models and demonstrate that our end-to-end baseline model achieves competitive results. This work offers a new benchmark for studying executable semantic parsing and contextual understanding in map-based query tasks.</abstract>
<identifier type="citekey">zhang-etal-2026-mto</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.36/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>750</start>
<end>771</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MTO: A Multi-turn Conversational Text-to-OverpassQL Dataset for Enhanced OpenStreetMap Query Generation
%A Zhang, Haodi
%A Zhu, Xinrui
%A Kong, Mingze
%A Liu, Zhidan
%A Fan, Tao
%A Wu, Kaishun
%A Song, Yuanfeng
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F zhang-etal-2026-mto
%X We propose a comprehensive framework for constructing multi-turn Text-to-OverpassQL dialogue datasets. Under this framework, we introduce the first multi-turn Text-to-OverpassQL dataset built upon the OverpassNL corpus. Our dataset comprises over 7,800 dialogues, each containing 2 to 4 user utterances, resulting in more than 20,000 individual utterances aligned with executable Overpass queries. To generate high-quality multi-turn dialogues, we design a four-stage pipeline. First, we convert Overpass queries into syntax trees using a custom parser developed based on the official OverpassQL grammar. This enables structural manipulation while preserving syntactic and executable validity. Second, we apply a diverse set of tree-editing templates, including both simple keyword-level changes and complex structural decompositions, to produce multiple valid and diverse Overpass queries. Third, we leverage a prompt-based approach to guide large language models in generating context-aware natural language questions, ensuring increasing inter-turn dependency across the dialogue. Finally, we implement a hybrid filtering strategy that combines manual annotation with model-assisted selection to validate alignment and correctness at scale. In addition to presenting the dataset, we evaluate the performance of several mainstream large language models and demonstrate that our end-to-end baseline model achieves competitive results. This work offers a new benchmark for studying executable semantic parsing and contextual understanding in map-based query tasks.
%U https://aclanthology.org/2026.findings-acl.36/
%P 750-771
Markdown (Informal)
[MTO: A Multi-turn Conversational Text-to-OverpassQL Dataset for Enhanced OpenStreetMap Query Generation](https://aclanthology.org/2026.findings-acl.36/) (Zhang et al., Findings 2026)
ACL
- 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. In Findings of the Association for Computational Linguistics: ACL 2026, pages 750–771, San Diego, California, United States. Association for Computational Linguistics.