Beyond Vanilla Fine-Tuning: Leveraging Multistage, Multilingual, and Domain-Specific Methods for Low-Resource Machine Translation

• URL: http://arxiv.org/abs/2503.22582v1
• Date: Fri, 28 Mar 2025 16:30:28 GMT
• Title: Beyond Vanilla Fine-Tuning: Leveraging Multistage, Multilingual, and Domain-Specific Methods for Low-Resource Machine Translation
• Authors: Sarubi Thillainathan, Songchen Yuan, En-Shiun Annie Lee, Sanath Jayasena, Surangika Ranathunga,
• Abstract summary: This paper contributes to artificial intelligence by proposing two approaches for adapting large language models (msLLMs)<n>As an application in engineering, these methods are implemented in NMT systems for Sinhala, Tamil, and English (six language pairs) in domain-specific, extremely low-resource settings.<n>Our experiments reveal that these approaches enhance translation performance by an average of +1.47 bilingual evaluation understudy (BLEU) score compared to the standard single-stage fine-tuning baseline.
• Score: 1.9639956888747314
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fine-tuning multilingual sequence-to-sequence large language models (msLLMs) has shown promise in developing neural machine translation (NMT) systems for low-resource languages (LRLs). However, conventional single-stage fine-tuning methods struggle in extremely low-resource NMT settings, where training data is very limited. This paper contributes to artificial intelligence by proposing two approaches for adapting msLLMs in these challenging scenarios: (1) continual pre-training (CPT), where the msLLM is further trained with domain-specific monolingual data to compensate for the under-representation of LRLs, and (2) intermediate task transfer learning (ITTL), a method that fine-tunes the msLLM with both in-domain and out-of-domain parallel data to enhance its translation capabilities across various domains and tasks. As an application in engineering, these methods are implemented in NMT systems for Sinhala, Tamil, and English (six language pairs) in domain-specific, extremely low-resource settings (datasets containing fewer than 100,000 samples). Our experiments reveal that these approaches enhance translation performance by an average of +1.47 bilingual evaluation understudy (BLEU) score compared to the standard single-stage fine-tuning baseline across all translation directions. Additionally, a multi-model ensemble further improves performance by an additional BLEU score.

Related papers

• Exploiting Domain-Specific Parallel Data on Multilingual Language Models for Low-resource Language Translation [0.6467856992131628]
  We present an evaluation of the effectiveness of parallel data from auxiliary domains in building domain-specific NMT models.<n>We explore the impact of domain divergence on NMT model performance.<n>We recommend several strategies for utilizing auxiliary parallel data in building domain-specific NMT models.
  arXiv  Detail & Related papers  (2024-12-27T08:25:52Z)
• Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning [55.107329995417786]
  Large language models (LLMs) have demonstrated impressive general understanding and generation abilities. We establish a benchmark for multi-domain translation, featuring 25 German$Leftrightarrow$English and 22 Chinese$Leftrightarrow$English test sets. We propose a domain Chain of Thought (CoT) fine-tuning technique that utilizes the intrinsic multi-domain intelligence of LLMs to improve translation performance.
  arXiv  Detail & Related papers  (2024-10-03T16:15:04Z)
• Relevance-guided Neural Machine Translation [5.691028372215281]
  We propose an explainability-based training approach for Neural Machine Translation (NMT) Our results show our method can be promising, particularly when training in low-resource conditions.
  arXiv  Detail & Related papers  (2023-11-30T21:52:02Z)
• Exploiting Language Relatedness in Machine Translation Through Domain Adaptation Techniques [3.257358540764261]
  We present a novel approach of using a scaled similarity score of sentences, especially for related languages based on a 5-gram KenLM language model. Our approach succeeds in increasing 2 BLEU point on multi-domain approach, 3 BLEU point on fine-tuning for NMT and 2 BLEU point on iterative back-translation approach.
  arXiv  Detail & Related papers  (2023-03-03T09:07:30Z)
• High-resource Language-specific Training for Multilingual Neural Machine Translation [109.31892935605192]
  We propose the multilingual translation model with the high-resource language-specific training (HLT-MT) to alleviate the negative interference. Specifically, we first train the multilingual model only with the high-resource pairs and select the language-specific modules at the top of the decoder. HLT-MT is further trained on all available corpora to transfer knowledge from high-resource languages to low-resource languages.
  arXiv  Detail & Related papers  (2022-07-11T14:33:13Z)
• Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation [50.54059385277964]
  We present a novel data augmentation paradigm termed Continuous Semantic Augmentation (CsaNMT) CsaNMT augments each training instance with an adjacency region that could cover adequate variants of literal expression under the same meaning.
  arXiv  Detail & Related papers  (2022-04-14T08:16:28Z)
• Improving Multilingual Translation by Representation and Gradient Regularization [82.42760103045083]
  We propose a joint approach to regularize NMT models at both representation-level and gradient-level. Our results demonstrate that our approach is highly effective in both reducing off-target translation occurrences and improving zero-shot translation performance.
  arXiv  Detail & Related papers  (2021-09-10T10:52:21Z)
• Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training [58.72619374790418]
  MultiUAT dynamically adjusts the training data usage based on the model's uncertainty. We analyze the cross-domain transfer and show the deficiency of static and similarity based methods.
  arXiv  Detail & Related papers  (2021-09-06T08:30:33Z)
• Multi-task Learning for Multilingual Neural Machine Translation [32.81785430242313]
  We propose a multi-task learning framework that jointly trains the model with the translation task on bitext data and two denoising tasks on the monolingual data. We show that the proposed approach can effectively improve the translation quality for both high-resource and low-resource languages.
  arXiv  Detail & Related papers  (2020-10-06T06:54:12Z)
• Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation [81.7786241489002]
  Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations. We argue that multilingual NMT requires stronger modeling capacity to support language pairs with varying typological characteristics. We propose random online backtranslation to enforce the translation of unseen training language pairs.
  arXiv  Detail & Related papers  (2020-04-24T17:21:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.