Challenge: Currently, machine translation systems cater to high-resource languages (HRLs), while low-resourced languages (LRLs) like Taiwanese Hokkien are relatively under-explored.
Approach: They propose to use a pre-trained LLaMA 2-7B model specialized in Traditional Mandarin Chinese to leverage orthographic similarities between Taiwanese Hokkien Han and Traditional Mandarin China.
Outcome: The proposed model bridges the gap between Taiwanese Hokkien and other low-resource languages by using a pre-trained LLaMA 2-7B model and a monolingual corpus.

Similar Papers

LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages (2024.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) exhibit exceptional translation capabilities in high-resource language tasks, yet their effectiveness in low-resourced languages is suboptimal.
Approach: They conduct extensive multilingual continual pre-training on the LLaMA series models and develop LLiMAX for translation support across more than 100 languages.
Outcome: The proposed model achieves higher translation performance than existing open-source models and performs on-par with specialized translation model on the Flores-101 benchmark.
Speech-to-Speech Translation for a Real-world Unwritten Language (2023.findings-acl)

Copied to clipboard

Challenge: a new study examines speech-to-speech translation (S2ST) that translates speech from one language into another . the research area for unwritten languages remains a research area with little exploration due to the lack of training data.
Approach: They propose a system that translates speech from one language into another . they use Taiwanese Hokkien as an example of an unwritten language .
Outcome: The proposed system can be used to train models in languages without standard writing systems.
Exploring Methods for Building Dialects-Mandarin Code-Mixing Corpora: A Case Study in Taiwanese Hokkien (2022.findings-emnlp)

Copied to clipboard

Challenge: CM is a challenging task when mixed languages include dialects.
Approach: They propose to construct a Hokkien-Mandarin CM dataset to overcome the limitation . they propose to use a linguistics-based toolkit to train the model for translation tasks .
Outcome: The proposed model achieves good results on CM data translation while maintaining monolingual translation quality.
Optimizing Language Augmentation for Multilingual Large Language Models: A Case Study on Korean (2024.lrec-main)

Copied to clipboard

Challenge: Large language models (LLMs) use pretraining to predict the subsequent word, but less-resourced languages are being overlooked.
Approach: They propose to expand the MLLM vocabularies to enhance expressiveness and use bilingual data for pretraining to align the high- and less-resourced languages.
Outcome: The proposed model outperforms existing models in qualitative analyses compared to Korean monolingual models.
CUTE: A Multilingual Dataset for Enhancing Cross-Lingual Knowledge Transfer in Low-Resource Languages (2025.coling-main)

Copied to clipboard

Challenge: Existing multilingual models such as XLM-R support only approximately 100-200 languages, leaving nearly 7,000 low-resource languages untapped.
Approach: They construct and open-source a dataset of four-language corpora obtained through machine translation into Chinese, Uyghur and Tibetan.
Outcome: The proposed dataset includes two resource-rich languages and two low-resource languages.
TOWER+: Bridging Generality and Translation Specialization in Multilingual LLMs (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are emerging as the de facto solution for multilingual machine translation.
Approach: They propose a suite of LLMs that can be fine-tuned to deliver strong performance on translation and multilingual general-purpose text capabilities.
Outcome: The proposed models outperform existing models on translation and general-purpose tasks.
A Novel Paradigm Boosting Translation Capabilities of Large Language Models (2024.findings-naacl)

Copied to clipboard

Challenge: Existing studies on LLMs focused on supervised fine-tuning but their effectiveness has been limited.
Approach: They propose a paradigm consisting of three stages: Secondary Pre-training using extensive monolingual data, Continual Pre- training with interlinear text format documents, and Leveraging source-language consistent instruction for supervised fine-tuning.
Outcome: The proposed approach surpasses previous work and achieves superior performance compared to models such as NLLB-54B(CITATION) and GPT3.5-text-davinci-003.
Back to School: Translation Using Grammar Books (2024.emnlp-main)

Copied to clipboard

Challenge: Current large language models require massive amounts of parallel sentences to perform machine translations for high resource languages.
Approach: They propose to incorporate grammar books into the prompt of GPT-4 to improve machine translation and evaluate the performance on 16 topologically diverse low-resource languages.
Outcome: The proposed method improves on 16 low-resource languages on 16 topologically diverse languages.
Multilingual Machine Translation: Closing the Gap between Shared and Language-specific Encoder-Decoders (2021.eacl-main)

Copied to clipboard

Challenge: State-of-the-art multilingual machine translation relies on a universal encoder-decoder, which requires retraining the entire system to add new languages.
Approach: They propose an encoder-decoder approach that can be extended to new languages by learning their corresponding modules.
Outcome: The proposed approach outperforms the universal encoder-decoder by 3.28 BLEU points on average while allowing to add new languages without retraining the rest of the modules.
Two Parents, One Child: Dual Transfer for Low-Resource Neural Machine Translation (2021.findings-acl)

Copied to clipboard

Challenge: Neural machine translation suffers when parallel data is scarce for training . a new framework to transfer multiple sources of auxiliary data is proposed .
Approach: They propose a framework to transfer multiple sources of auxiliary data from high-resource parallel data to low-resourced translation models using pretrained language models.
Outcome: The proposed approach yields consistent improvements over strong competitors for multiple translation directions.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations