@inproceedings{shuvo-mondal-2026-bd,
title = "{BD}-{A}gri{KG}: A Knowledge Graph and Bilingual {T}ext2{C}ypher Benchmark for Crop Suitability and Productivity in {B}angladesh",
author = "Shuvo, Md. Aukerul Moin and
Mondal, Md Nazrul Islam",
editor = "Er-Rahmadi, Btissam and
Montella, S{\'e}bastien and
Graux, Damien and
Melo, Andr{\'e} and
Jabeen, Hajira",
booktitle = "Proceedings of the 3rd Workshop on {KNO}wledge {GR}aphs Agentic Systems Interplay ({NORA} 2026)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.nora-1.6/",
pages = "63--76",
ISBN = "979-8-89176-457-6",
abstract = "Agricultural advisory in Bangladesh rests on public statistics locked in PDF yearbooks, and on language technology that rarely speaks Bangla. We present BD-AgriKG, a knowledge graph that integrates five government sources on one administrative spine keyed by standard place codes: upazila-level land suitability for 16 crops, agro-meteorological thresholds, crop calendars, soil associations, and a newly extracted district production panel covering twelve crop years, validated against the yearbooks' own published totals. On top of the graph we release what is, to our knowledge, the first bilingual (English and Bangla) execution-based Text2Cypher benchmark: 460 questions instantiating 26 templates, built Cypher-first so that every item carries an executable gold query and a non-empty executed answer. We report execution-accuracy baselines for seven large language models (LLMs) in both languages. The best model reaches 95.2{\%} in English and 90.9{\%} in Bangla under a strict exact-projection metric whose frontier failures are almost all extra returned columns. Every model scores lower in Bangla, by 1 to 14 points; after multiple-comparison correction the gap is significant for three of the seven models under a template-clustered bootstrap and for one under template-level tests, and for four models, both frontier models among them, two question templates carry most of it. One turn of execution feedback, the simplest use of the graph{'}s own execution signal, recovers 43-73{\%} of the invalid and empty failures of mid-tier models and helps Bangla at least as much as English, though not significantly more, while small open models recover almost nothing. The graph, panel, benchmark and harness are released."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shuvo-mondal-2026-bd">
<titleInfo>
<title>BD-AgriKG: A Knowledge Graph and Bilingual Text2Cypher Benchmark for Crop Suitability and Productivity in Bangladesh</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Aukerul</namePart>
<namePart type="given">Moin</namePart>
<namePart type="family">Shuvo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Nazrul</namePart>
<namePart type="given">Islam</namePart>
<namePart type="family">Mondal</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>Proceedings of the 3rd Workshop on KNOwledge GRaphs Agentic Systems Interplay (NORA 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Btissam</namePart>
<namePart type="family">Er-Rahmadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sébastien</namePart>
<namePart type="family">Montella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damien</namePart>
<namePart type="family">Graux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Melo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hajira</namePart>
<namePart type="family">Jabeen</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">979-8-89176-457-6</identifier>
</relatedItem>
<abstract>Agricultural advisory in Bangladesh rests on public statistics locked in PDF yearbooks, and on language technology that rarely speaks Bangla. We present BD-AgriKG, a knowledge graph that integrates five government sources on one administrative spine keyed by standard place codes: upazila-level land suitability for 16 crops, agro-meteorological thresholds, crop calendars, soil associations, and a newly extracted district production panel covering twelve crop years, validated against the yearbooks’ own published totals. On top of the graph we release what is, to our knowledge, the first bilingual (English and Bangla) execution-based Text2Cypher benchmark: 460 questions instantiating 26 templates, built Cypher-first so that every item carries an executable gold query and a non-empty executed answer. We report execution-accuracy baselines for seven large language models (LLMs) in both languages. The best model reaches 95.2% in English and 90.9% in Bangla under a strict exact-projection metric whose frontier failures are almost all extra returned columns. Every model scores lower in Bangla, by 1 to 14 points; after multiple-comparison correction the gap is significant for three of the seven models under a template-clustered bootstrap and for one under template-level tests, and for four models, both frontier models among them, two question templates carry most of it. One turn of execution feedback, the simplest use of the graph’s own execution signal, recovers 43-73% of the invalid and empty failures of mid-tier models and helps Bangla at least as much as English, though not significantly more, while small open models recover almost nothing. The graph, panel, benchmark and harness are released.</abstract>
<identifier type="citekey">shuvo-mondal-2026-bd</identifier>
<location>
<url>https://aclanthology.org/2026.nora-1.6/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>63</start>
<end>76</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BD-AgriKG: A Knowledge Graph and Bilingual Text2Cypher Benchmark for Crop Suitability and Productivity in Bangladesh
%A Shuvo, Md. Aukerul Moin
%A Mondal, Md Nazrul Islam
%Y Er-Rahmadi, Btissam
%Y Montella, Sébastien
%Y Graux, Damien
%Y Melo, André
%Y Jabeen, Hajira
%S Proceedings of the 3rd Workshop on KNOwledge GRaphs Agentic Systems Interplay (NORA 2026)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-457-6
%F shuvo-mondal-2026-bd
%X Agricultural advisory in Bangladesh rests on public statistics locked in PDF yearbooks, and on language technology that rarely speaks Bangla. We present BD-AgriKG, a knowledge graph that integrates five government sources on one administrative spine keyed by standard place codes: upazila-level land suitability for 16 crops, agro-meteorological thresholds, crop calendars, soil associations, and a newly extracted district production panel covering twelve crop years, validated against the yearbooks’ own published totals. On top of the graph we release what is, to our knowledge, the first bilingual (English and Bangla) execution-based Text2Cypher benchmark: 460 questions instantiating 26 templates, built Cypher-first so that every item carries an executable gold query and a non-empty executed answer. We report execution-accuracy baselines for seven large language models (LLMs) in both languages. The best model reaches 95.2% in English and 90.9% in Bangla under a strict exact-projection metric whose frontier failures are almost all extra returned columns. Every model scores lower in Bangla, by 1 to 14 points; after multiple-comparison correction the gap is significant for three of the seven models under a template-clustered bootstrap and for one under template-level tests, and for four models, both frontier models among them, two question templates carry most of it. One turn of execution feedback, the simplest use of the graph’s own execution signal, recovers 43-73% of the invalid and empty failures of mid-tier models and helps Bangla at least as much as English, though not significantly more, while small open models recover almost nothing. The graph, panel, benchmark and harness are released.
%U https://aclanthology.org/2026.nora-1.6/
%P 63-76
Markdown (Informal)
[BD-AgriKG: A Knowledge Graph and Bilingual Text2Cypher Benchmark for Crop Suitability and Productivity in Bangladesh](https://aclanthology.org/2026.nora-1.6/) (Shuvo & Mondal, NORA 2026)
ACL