Chandomitra: Towards Generating Structured Sanskrit Poetry from Natural Language Inputs
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915734992453632 |
|---|---|
| author | Jagadeeshan, Manoj Balaji Bhatia, Samarth Ray, Pretam Surana, Harshul Raj P, Akhil Rajeev Mishra, Priya Kulkarni, Annarao Ramakrishnan, Ganesh AP, Prathosh Goyal, Pawan |
| author_facet | Jagadeeshan, Manoj Balaji Bhatia, Samarth Ray, Pretam Surana, Harshul Raj P, Akhil Rajeev Mishra, Priya Kulkarni, Annarao Ramakrishnan, Ganesh AP, Prathosh Goyal, Pawan |
| contents | 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. Data and Code are available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00815 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Chandomitra: Towards Generating Structured Sanskrit Poetry from Natural Language Inputs Jagadeeshan, Manoj Balaji Bhatia, Samarth Ray, Pretam Surana, Harshul Raj P, Akhil Rajeev Mishra, Priya Kulkarni, Annarao Ramakrishnan, Ganesh AP, Prathosh Goyal, Pawan Computation and Language 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. Data and Code are available. |
| title | Chandomitra: Towards Generating Structured Sanskrit Poetry from Natural Language Inputs |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.00815 |