@inproceedings{rakshit-flanigan-2025-alankaar,
title = "Alankaar: A Dataset for Figurativeness Understanding in {B}angla",
author = "Rakshit, Geetanjali and
Flanigan, Jeffrey",
editor = "Angelova, Galia and
Kunilovskaya, Maria and
Escribe, Marie and
Mitkov, Ruslan",
booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-1.114/",
pages = "998--1002",
abstract = "Bangla has a rich written literature, automatically making it replete with examples of creative usage of language. There have been limited efforts to computationally analyze creative text in the Bangla language due to a lack of resources. We present Alankaar, a dataset of 2500 manually annotated examples of text fragments in Bangla containing metaphors. We also provide automatic and manual English translations of these examples. Additionally, we provide 2500 examples of non-metaphorical text in Bangla. We use this dataset to build a metaphor identification system in Bangla. We also use it as a test bed for cross-lingual metaphor translation, finding that not all metaphors translate literally across languages and there are several cultural factors at play in the translation of metaphors. We hope this will advance the field in metaphor translation research and in grounding cultural nuances at work in the process of machine translation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rakshit-flanigan-2025-alankaar">
<titleInfo>
<title>Alankaar: A Dataset for Figurativeness Understanding in Bangla</title>
</titleInfo>
<name type="personal">
<namePart type="given">Geetanjali</namePart>
<namePart type="family">Rakshit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeffrey</namePart>
<namePart type="family">Flanigan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Escribe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Bangla has a rich written literature, automatically making it replete with examples of creative usage of language. There have been limited efforts to computationally analyze creative text in the Bangla language due to a lack of resources. We present Alankaar, a dataset of 2500 manually annotated examples of text fragments in Bangla containing metaphors. We also provide automatic and manual English translations of these examples. Additionally, we provide 2500 examples of non-metaphorical text in Bangla. We use this dataset to build a metaphor identification system in Bangla. We also use it as a test bed for cross-lingual metaphor translation, finding that not all metaphors translate literally across languages and there are several cultural factors at play in the translation of metaphors. We hope this will advance the field in metaphor translation research and in grounding cultural nuances at work in the process of machine translation.</abstract>
<identifier type="citekey">rakshit-flanigan-2025-alankaar</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.114/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>998</start>
<end>1002</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Alankaar: A Dataset for Figurativeness Understanding in Bangla
%A Rakshit, Geetanjali
%A Flanigan, Jeffrey
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F rakshit-flanigan-2025-alankaar
%X Bangla has a rich written literature, automatically making it replete with examples of creative usage of language. There have been limited efforts to computationally analyze creative text in the Bangla language due to a lack of resources. We present Alankaar, a dataset of 2500 manually annotated examples of text fragments in Bangla containing metaphors. We also provide automatic and manual English translations of these examples. Additionally, we provide 2500 examples of non-metaphorical text in Bangla. We use this dataset to build a metaphor identification system in Bangla. We also use it as a test bed for cross-lingual metaphor translation, finding that not all metaphors translate literally across languages and there are several cultural factors at play in the translation of metaphors. We hope this will advance the field in metaphor translation research and in grounding cultural nuances at work in the process of machine translation.
%U https://aclanthology.org/2025.ranlp-1.114/
%P 998-1002
Markdown (Informal)
[Alankaar: A Dataset for Figurativeness Understanding in Bangla](https://aclanthology.org/2025.ranlp-1.114/) (Rakshit & Flanigan, RANLP 2025)
ACL
- Geetanjali Rakshit and Jeffrey Flanigan. 2025. Alankaar: A Dataset for Figurativeness Understanding in Bangla. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 998–1002, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.