Translating Classical Poetry into Modern Prose

Chalamalasetti Kranti; Sowmya Vajjala

cs.CLJun 1, 2026

Translating Classical Poetry into Modern Prose

Authors: Chalamalasetti Kranti, Sowmya Vajjala

Organizations: Computational Linguistics, University of Potsdam, Germany · National Research Council, Ottawa, Canada

Abstract

We built a dataset for the task of poem-to-prose translation from 13th-17th Century Telugu classical poetry to contemporary Telugu and English prose, which we call Padyam2Gadyam. The dataset consists of 600 poems and their human-verified Telugu and English prose translations. We evaluated 2 machine translation systems and 5 contemporary Large Language Models (LLMs) on their ability to do zero-shot poem-to-prose translation into Telugu and English using this dataset. Our results indicate that while the general purpose LLMs are better than the machine translation systems, there are systematic issues with the generation and evaluation of prose translation in both languages across systems.

Explore similar work

System Report for CCL25-Eval Task 5: New Dataset and LoRA-Fine-Tuned Qwen2.5
Jun 10, 2026Haotao XiePoetry Natural Language Datasets
PaliBench: A Multi-Reference Blueprint for Classical Language Translation Benchmarks
May 16, 2026Máté Metzger, Nadnapang PhophichitMultilingual Benchmark Bodhi
Poller: Are LLMs Suitable for Evaluating the Poetry Understanding Task?
Jun 29, 2026Shanshan Wang, Derek F. Wong, Jingming Yao +1Poetry Large Language Model Evaluation

Jun 10, 2026 · cs.CLJ/K move · Enter open · S save

System Report for CCL25-Eval Task 5: New Dataset and LoRA-Fine-Tuned Qwen2.5

Haotao Xie

Recently, large language models (LLMs) have achieved promising progress in the fields of classical Chinese translation and the generation of classical poetry. However, domain-specific research on precise translation and affective-semantic understanding of classical poetry remains limited. The main challenge is that most studies treat the poetic appreciation task as a general-domain problem, neglecting the distinctive features of poetic appreciation, while high-quality and domain-specific datasets are extremely limited. To address this limitation, we decompose the task into three subtasks: term interpretation, semantic interpretation, and emotional inference. Based on multiple open-source datasets, we perform data cleansing and alignment to construct the Classical Chinese Poetry Instruction Pair Dataset (CCPoetry-49K), which comprises 49,404 high-quality instruction-response pairs explicitly optimized for this domain. We then propose a domain-specialized LLM, called PoetryQwen, by applying Low-Rank Adaptation (LoRA) to fine-tune the Qwen2.5-14B model. Experimental results on the CCL25-Eval Task 5 benchmark demonstrate that PoetryQwen achieves a score of 0.757, representing a 9.7% improvement over the Qwen2.5-14B-Instruct baseline (0.690). These findings clearly indicate that PoetryQwen significantly enhances performance in precise translation and emotional understanding of classical poetry. We present new dataset and methodological considerations intended to support the domain-specific optimization of LLMs.

Poetry Natural Language Datasets Domain-Specific Language

Open paper Ask about it PDF

Abstract

Explore similar work

System Report for CCL25-Eval Task 5: New Dataset and LoRA-Fine-Tuned Qwen2.5

PaliBench: A Multi-Reference Blueprint for Classical Language Translation Benchmarks

Poller: Are LLMs Suitable for Evaluating the Poetry Understanding Task?