@inproceedings{zheng-etal-2026-ecql,
title = "{ECQL}: An Executable Benchmark for Auditable Corpus Query Semantic Parsing",
author = "Zheng, Yuxi and
Liu, Yeqing and
Zhou, Ziming and
Wang, Xiaodong and
Zhang, Yongwei and
Yu, Jingsong",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.3/",
pages = "35--44",
ISBN = "979-8-89176-444-6",
abstract = "Corpus Query Language (CQL) supports precise corpus analysis but requires expertise in annotations, regular expressions, structural scopes, and platform-specific syntax. Natural-language interfaces simplify access, but their answers can be difficult to inspect, reproduce, or revise. We study Text-to-CQL as executable semantic parsing, mapping intents to inspectable queries. We introduce ECQL, a Sketch-Engine-oriented benchmark of 3,572 natural language{--}CQL pairs comprising 811 tutorial-derived and 2,761 synthetic examples, with a default split of 3,215 training and 357 test examples. ECQL focuses on Sketch Engine normalization, CQL Diagnostic Profile (CQL-DP) annotations, controlled semantic contrasts, audit-oriented metadata, and generalization protocols, alongside an evaluation suite covering syntactic validity, exact match, canonical match, and execution match. The full 357-example headline test set is independently double-annotated and adjudicated, with 96.9{\%} agreement for intent clarity, 94.7{\%} agreement for CQL{--}intent alignment, and a 3.1{\%} post-adjudication intent-match error rate. Experiments with prompting, retrieval-augmented prompting, syntax repair, DeepSeek-R1 reasoning prompting, a GPT-4o Agent/API alternative, and supervised fine-tuning reveal persistent difficulties with corpus-query semantics. The best fine-tuned model reaches 85.6{\%} execution accuracy on the random split, but drops to 68.9{\%} on template-disjoint evaluation. ECQL provides a reproducible testbed for auditable semantic parsing over specialized linguistic query languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-etal-2026-ecql">
<titleInfo>
<title>ECQL: An Executable Benchmark for Auditable Corpus Query Semantic Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuxi</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yeqing</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziming</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongwei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingsong</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Corpus Query Language (CQL) supports precise corpus analysis but requires expertise in annotations, regular expressions, structural scopes, and platform-specific syntax. Natural-language interfaces simplify access, but their answers can be difficult to inspect, reproduce, or revise. We study Text-to-CQL as executable semantic parsing, mapping intents to inspectable queries. We introduce ECQL, a Sketch-Engine-oriented benchmark of 3,572 natural language–CQL pairs comprising 811 tutorial-derived and 2,761 synthetic examples, with a default split of 3,215 training and 357 test examples. ECQL focuses on Sketch Engine normalization, CQL Diagnostic Profile (CQL-DP) annotations, controlled semantic contrasts, audit-oriented metadata, and generalization protocols, alongside an evaluation suite covering syntactic validity, exact match, canonical match, and execution match. The full 357-example headline test set is independently double-annotated and adjudicated, with 96.9% agreement for intent clarity, 94.7% agreement for CQL–intent alignment, and a 3.1% post-adjudication intent-match error rate. Experiments with prompting, retrieval-augmented prompting, syntax repair, DeepSeek-R1 reasoning prompting, a GPT-4o Agent/API alternative, and supervised fine-tuning reveal persistent difficulties with corpus-query semantics. The best fine-tuned model reaches 85.6% execution accuracy on the random split, but drops to 68.9% on template-disjoint evaluation. ECQL provides a reproducible testbed for auditable semantic parsing over specialized linguistic query languages.</abstract>
<identifier type="citekey">zheng-etal-2026-ecql</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.3/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>35</start>
<end>44</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ECQL: An Executable Benchmark for Auditable Corpus Query Semantic Parsing
%A Zheng, Yuxi
%A Liu, Yeqing
%A Zhou, Ziming
%A Wang, Xiaodong
%A Zhang, Yongwei
%A Yu, Jingsong
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F zheng-etal-2026-ecql
%X Corpus Query Language (CQL) supports precise corpus analysis but requires expertise in annotations, regular expressions, structural scopes, and platform-specific syntax. Natural-language interfaces simplify access, but their answers can be difficult to inspect, reproduce, or revise. We study Text-to-CQL as executable semantic parsing, mapping intents to inspectable queries. We introduce ECQL, a Sketch-Engine-oriented benchmark of 3,572 natural language–CQL pairs comprising 811 tutorial-derived and 2,761 synthetic examples, with a default split of 3,215 training and 357 test examples. ECQL focuses on Sketch Engine normalization, CQL Diagnostic Profile (CQL-DP) annotations, controlled semantic contrasts, audit-oriented metadata, and generalization protocols, alongside an evaluation suite covering syntactic validity, exact match, canonical match, and execution match. The full 357-example headline test set is independently double-annotated and adjudicated, with 96.9% agreement for intent clarity, 94.7% agreement for CQL–intent alignment, and a 3.1% post-adjudication intent-match error rate. Experiments with prompting, retrieval-augmented prompting, syntax repair, DeepSeek-R1 reasoning prompting, a GPT-4o Agent/API alternative, and supervised fine-tuning reveal persistent difficulties with corpus-query semantics. The best fine-tuned model reaches 85.6% execution accuracy on the random split, but drops to 68.9% on template-disjoint evaluation. ECQL provides a reproducible testbed for auditable semantic parsing over specialized linguistic query languages.
%U https://aclanthology.org/2026.findings-aacl.3/
%P 35-44
Markdown (Informal)
[ECQL: An Executable Benchmark for Auditable Corpus Query Semantic Parsing](https://aclanthology.org/2026.findings-aacl.3/) (Zheng et al., Findings 2026)
ACL