@inproceedings{jagadeeshan-etal-2026-chandomitra,
title = "Chandomitra: Towards Generating Structured {S}anskrit Poetry from Natural Language Inputs",
author = "Jagadeeshan, Manoj Balaji and
Bhatia, Samarth and
Ray, Pretam and
Surana, Harshul Raj and
P, Akhil Rajeev and
Mishra, Priya and
Kulkarni, Annarao and
Ramakrishnan, Ganesh and
Ap, Prathosh and
Goyal, Pawan",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-long.24/",
pages = "518--534",
ISBN = "979-8-89176-380-7",
abstract = "Text Generation has achieved remarkable performance using large language models. It has also been recently well-studied that these large language models are capable of creative generation tasks but prominently for high-resource languages. This prompts a fundamental question: $\textit{Is there a way to utilize these (large) language models for structured poetry generation in a low-resource language, such as Sanskrit?}$ We present Chandomitra, an English input to structured Sanskrit Poetry translation dataset, specifically adhering to the Anushtubh meter. We benchmark various open and closed models, and scrutinize specialized techniques such as constrained decoding and instruction fine-tuning, for the proposed task. Our constrained decoding methodology achieves 99.86{\%} syntactic accuracy in generating metrically valid Sanskrit poetry, outperforming GPT-4o (1-shot: 31.24{\%}). Our best-performing instruction-tuned model, on the other hand, performs better in semantic coherence with the English input, at the expense of slightly lower syntactic accuracy. Human evaluation further reveals that instruction fine-tuned model is better able to capture the poetic aspects."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jagadeeshan-etal-2026-chandomitra">
<titleInfo>
<title>Chandomitra: Towards Generating Structured Sanskrit Poetry from Natural Language Inputs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manoj</namePart>
<namePart type="given">Balaji</namePart>
<namePart type="family">Jagadeeshan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samarth</namePart>
<namePart type="family">Bhatia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pretam</namePart>
<namePart type="family">Ray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harshul</namePart>
<namePart type="given">Raj</namePart>
<namePart type="family">Surana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akhil</namePart>
<namePart type="given">Rajeev</namePart>
<namePart type="family">P</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priya</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annarao</namePart>
<namePart type="family">Kulkarni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ganesh</namePart>
<namePart type="family">Ramakrishnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prathosh</namePart>
<namePart type="family">Ap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pawan</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-380-7</identifier>
</relatedItem>
<abstract>Text Generation has achieved remarkable performance using large language models. It has also been recently well-studied that these large language models are capable of creative generation tasks but prominently for high-resource languages. This prompts a fundamental question: Is there a way to utilize these (large) language models for structured poetry generation in a low-resource language, such as Sanskrit? We present Chandomitra, an English input to structured Sanskrit Poetry translation dataset, specifically adhering to the Anushtubh meter. We benchmark various open and closed models, and scrutinize specialized techniques such as constrained decoding and instruction fine-tuning, for the proposed task. Our constrained decoding methodology achieves 99.86% syntactic accuracy in generating metrically valid Sanskrit poetry, outperforming GPT-4o (1-shot: 31.24%). Our best-performing instruction-tuned model, on the other hand, performs better in semantic coherence with the English input, at the expense of slightly lower syntactic accuracy. Human evaluation further reveals that instruction fine-tuned model is better able to capture the poetic aspects.</abstract>
<identifier type="citekey">jagadeeshan-etal-2026-chandomitra</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-long.24/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>518</start>
<end>534</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Chandomitra: Towards Generating Structured Sanskrit Poetry from Natural Language Inputs
%A Jagadeeshan, Manoj Balaji
%A Bhatia, Samarth
%A Ray, Pretam
%A Surana, Harshul Raj
%A P, Akhil Rajeev
%A Mishra, Priya
%A Kulkarni, Annarao
%A Ramakrishnan, Ganesh
%A Ap, Prathosh
%A Goyal, Pawan
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-380-7
%F jagadeeshan-etal-2026-chandomitra
%X Text Generation has achieved remarkable performance using large language models. It has also been recently well-studied that these large language models are capable of creative generation tasks but prominently for high-resource languages. This prompts a fundamental question: Is there a way to utilize these (large) language models for structured poetry generation in a low-resource language, such as Sanskrit? We present Chandomitra, an English input to structured Sanskrit Poetry translation dataset, specifically adhering to the Anushtubh meter. We benchmark various open and closed models, and scrutinize specialized techniques such as constrained decoding and instruction fine-tuning, for the proposed task. Our constrained decoding methodology achieves 99.86% syntactic accuracy in generating metrically valid Sanskrit poetry, outperforming GPT-4o (1-shot: 31.24%). Our best-performing instruction-tuned model, on the other hand, performs better in semantic coherence with the English input, at the expense of slightly lower syntactic accuracy. Human evaluation further reveals that instruction fine-tuned model is better able to capture the poetic aspects.
%U https://aclanthology.org/2026.eacl-long.24/
%P 518-534
Markdown (Informal)
[Chandomitra: Towards Generating Structured Sanskrit Poetry from Natural Language Inputs](https://aclanthology.org/2026.eacl-long.24/) (Jagadeeshan et al., EACL 2026)
ACL
- Manoj Balaji Jagadeeshan, Samarth Bhatia, Pretam Ray, Harshul Raj Surana, Akhil Rajeev P, Priya Mishra, Annarao Kulkarni, Ganesh Ramakrishnan, Prathosh Ap, and Pawan Goyal. 2026. Chandomitra: Towards Generating Structured Sanskrit Poetry from Natural Language Inputs. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 518–534, Rabat, Morocco. Association for Computational Linguistics.