paper-with-me

홈 › Papers

BM25-Augmented Many-Shot Translation for Low-Resource North-Eastern Indian Languages

2026-08-13 · Aashish Dhawan, Christopher Driggers-Ellis, Dzmitry Kasinets, Christan Grant, Daisy Zhe Wang arxiv

This paper describes the University of Florida Gators submission to the WMT26 Low-Resource Indic Language Translation shared task. We adapt the retrieval-augmented many-shot translation pipeline from our AmericasNLP 2026 system to translate between English and eleven North-Eastern Indian languages in both directions. At inference time, BM25 retrieves the most similar parallel examples from a language-specific training bank, and Gemini 2.5 Flash translates the input conditioned on these examples. No model fine-tuning is involved. Training banks combine official WMT26 data with publicly available corpora such as Samanantar and prior WMT shared task releases. A grid search over retrieval count r and development exemplar count d across all 22 language-direction pairs selects the best configuration for each submission.

📄 PDF Abstract BibTeX arXiv:2608.13722

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Zero-shot North Korean to English Neural Machine Translation by Character Tokenization and Phoneme Decomposition

2020-07-01 · ACL 2020 6 · Hwichan Kim, Tosho Hirasawa, Mamoru Komachi

The primary limitation of North Korean to English translation is the lack of a parallel corpus; therefore, high translation accuracy cannot be achieved. To address this problem, we propose a zero-shot approach using Sout…

Machine TranslationTranslation

MALM: Mixing Augmented Language Modeling for Zero-Shot Machine Translation

2022-10-01 · Kshitij Gupta

Large pre-trained language models have brought remarkable progress in NLP. Pre-training and Fine-tuning have given state-of-art performance across tasks in text processing. Data Augmentation techniques have also helped b…

Data AugmentationLanguage ModelingLanguage ModellingMachine Translation+2

Learning How to Translate North Korean through South Korean

2022-01-27 · LREC 2022 6 · Hwichan Kim, Sangwhan Moon, Naoaki Okazaki, Mamoru Komachi

South and North Korea both use the Korean language. However, Korean NLP research has focused on South Korean only, and existing NLP systems of the Korean language, such as neural machine translation (NMT) models, cannot …

Machine TranslationNMTTranslation

EdinSaar@WMT21: North-Germanic Low-Resource Multilingual NMT

2021-09-29 · WMT (EMNLP) 2021 11 · Svetlana Tchistiakova, Jesujoba Alabi, Koel Dutta Chowdhury, Sourav Dutta 외

We describe the EdinSaar submission to the shared task of Multilingual Low-Resource Translation for North Germanic Languages at the Sixth Conference on Machine Translation (WMT2021). We submit multilingual translation mo…

Machine TranslationNMTTranslation

An Online Dictionary for Dialects of North Frisian

2022-06-01 · EURALI (LREC) 2022 6 · Michael Wehar, Tanno Hüttenrauch

Language is an essential part of communication and culture. Documenting, digitizing, and preserving language is a meaningful pursuit. The first author of this work is a speaker of Söl’ring which is a dialect of the North…

Cultural Vocal Bursts Intensity Prediction