Views
No views yet
>>ita<< for translating to Italian and >>lld_Latn<< for translating to Ladin (Val Badia).>>ita<< for translating to Italian and >>lld_Latn<< for translating to Ladin (Val Badia).1@inproceedings{frontull-moser-2024-rule,
2 title = "Rule-Based, Neural and {LLM} Back-Translation: Comparative Insights from a Variant of {L}adin",
3 author = "Frontull, Samuel and
4 Moser, Georg",
5 editor = "Ojha, Atul Kr. and
6 Liu, Chao-hong and
7 Vylomova, Ekaterina and
8 Pirinen, Flammie and
9 Abbott, Jade and
10 Washington, Jonathan and
11 Oco, Nathaniel and
12 Malykh, Valentin and
13 Logacheva, Varvara and
14 Zhao, Xiaobing",
15 booktitle = "Proceedings of the The Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024)",
16 month = aug,
17 year = "2024",
18 address = "Bangkok, Thailand",
19 publisher = "Association for Computational Linguistics",
20 url = "https://aclanthology.org/2024.loresmt-1.13",
21 pages = "128--138",
22 abstract = "This paper explores the impact of different back-translation approaches on machine translation for Ladin, specifically the Val Badia variant. Given the limited amount of parallel data available for this language (only 18k Ladin-Italian sentence pairs), we investigate the performance of a multilingual neural machine translation model fine-tuned for Ladin-Italian. In addition to the available authentic data, we synthesise further translations by using three different models: a fine-tuned neural model, a rule-based system developed specifically for this language pair, and a large language model. Our experiments show that all approaches achieve comparable translation quality in this low-resource scenario, yet round-trip translations highlight differences in model performance.",
23}