Don't Go Far Off: An Empirical Study on Neural Poetry Translation
arXiv:2109.02972
Abstract
Despite constant improvements in machine translation quality, automatic poetry translation remains a challenging problem due to the lack of open-sourced parallel poetic corpora, and to the intrinsic complexities involved in preserving the semantics, style, and figurative nature of poetry. We present an empirical investigation for poetry translation along several dimensions: 1) size and style of training data (poetic vs. non-poetic), including a zero-shot setup; 2) bilingual vs. multilingual learning; and 3) language-family-specific models vs. mixed-multilingual models. To accomplish this, we contribute a parallel dataset of poetry translations for several language pairs. Our results show that multilingual fine-tuning on poetic text significantly outperforms multilingual fine-tuning on non-poetic text that is 35X larger in size, both in terms of automatic metrics (BLEU, BERTScore) and human evaluation metrics such as faithfulness (meaning and poetic style). Moreover, multilingual fine-tuning on poetic data outperforms \emph{bilingual} fine-tuning on poetic data.
EMNLP 2021 Camera ready
References in corpus (6)
- Multilingual Denoising Pre-training for Neural Machine Translation
- DeBERTa: Decoding-enhanced BERT with Disentangled Attention
- Multilingual Translation with Extensible Multilingual Pretraining and Finetuning
- To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation
- An Empirical Comparison of Simple Domain Adaptation Methods for Neural Machine Translation
- An Iterative Polishing Framework based on Quality Aware Masked Language Model for Chinese Poetry Generation