@inproceedings{talukder-shahariar-2026-bangla,
title = "{B}angla {K}ey2{T}ext: Text Generation from Keywords for a Low Resource Language",
author = "Talukder, Tonmoy and
Shahariar, G M",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.303/",
doi = "10.63317/4wkpwaxktwfn",
pages = "3805--3822",
abstract = "This paper introduces Bangla Key2Text, a large-scale dataset of 2.6 million Bangla keyword-text pairs designed for keyword-driven text generation in a low-resource language. The dataset is constructed using a BERT-based keyword extraction pipeline applied to millions of Bangla news texts, transforming raw articles into structured keyword-text pairs suitable for supervised learning. To establish baseline performance on this new benchmark, we fine-tune two sequence-to-sequence models, mT5 and BanglaT5, and evaluate them using multiple automatic metrics and human judgments. Experimental results show that task-specific fine-tuning substantially improves keyword-conditioned text generation in Bangla compared to zero-shot large language models. The dataset, trained models, and code are publicly released to support future research in Bangla natural language generation and keyword-to-text generation tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="talukder-shahariar-2026-bangla">
<titleInfo>
<title>Bangla Key2Text: Text Generation from Keywords for a Low Resource Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tonmoy</namePart>
<namePart type="family">Talukder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">G</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Shahariar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces Bangla Key2Text, a large-scale dataset of 2.6 million Bangla keyword-text pairs designed for keyword-driven text generation in a low-resource language. The dataset is constructed using a BERT-based keyword extraction pipeline applied to millions of Bangla news texts, transforming raw articles into structured keyword-text pairs suitable for supervised learning. To establish baseline performance on this new benchmark, we fine-tune two sequence-to-sequence models, mT5 and BanglaT5, and evaluate them using multiple automatic metrics and human judgments. Experimental results show that task-specific fine-tuning substantially improves keyword-conditioned text generation in Bangla compared to zero-shot large language models. The dataset, trained models, and code are publicly released to support future research in Bangla natural language generation and keyword-to-text generation tasks.</abstract>
<identifier type="citekey">talukder-shahariar-2026-bangla</identifier>
<identifier type="doi">10.63317/4wkpwaxktwfn</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.303/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>3805</start>
<end>3822</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bangla Key2Text: Text Generation from Keywords for a Low Resource Language
%A Talukder, Tonmoy
%A Shahariar, G. M.
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F talukder-shahariar-2026-bangla
%X This paper introduces Bangla Key2Text, a large-scale dataset of 2.6 million Bangla keyword-text pairs designed for keyword-driven text generation in a low-resource language. The dataset is constructed using a BERT-based keyword extraction pipeline applied to millions of Bangla news texts, transforming raw articles into structured keyword-text pairs suitable for supervised learning. To establish baseline performance on this new benchmark, we fine-tune two sequence-to-sequence models, mT5 and BanglaT5, and evaluate them using multiple automatic metrics and human judgments. Experimental results show that task-specific fine-tuning substantially improves keyword-conditioned text generation in Bangla compared to zero-shot large language models. The dataset, trained models, and code are publicly released to support future research in Bangla natural language generation and keyword-to-text generation tasks.
%R 10.63317/4wkpwaxktwfn
%U https://aclanthology.org/2026.lrec-1.303/
%U https://doi.org/10.63317/4wkpwaxktwfn
%P 3805-3822
Markdown (Informal)
[Bangla Key2Text: Text Generation from Keywords for a Low Resource Language](https://aclanthology.org/2026.lrec-1.303/) (Talukder & Shahariar, LREC 2026)
ACL