Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning

• URL: http://arxiv.org/abs/2410.02631v1
• Date: Thu, 3 Oct 2024 16:15:04 GMT
• Title: Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning
• Authors: Tianxiang Hu, Pei Zhang, Baosong Yang, Jun Xie, Derek F. Wong, Rui Wang,
• Abstract summary: 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.
• Score: 55.107329995417786
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Achieving consistent high-quality machine translation (MT) across diverse domains remains a significant challenge, primarily due to the limited and imbalanced parallel training data available in various domains. While large language models (LLMs) have demonstrated impressive general understanding and generation abilities, their potential in multi-domain MT is under-explored. We establish a comprehensive benchmark for multi-domain translation, featuring 25 German$\Leftrightarrow$English and 22 Chinese$\Leftrightarrow$English test sets respectively covering 15 domains. Our evaluation of prominent LLMs reveals a discernible performance gap against traditional MT systems, highlighting domain overfitting and catastrophic forgetting issues after fine-tuning on domain-limited corpora. To mitigate this, we propose a domain Chain of Thought (CoT) fine-tuning technique that utilizes the intrinsic multi-domain intelligence of LLMs to improve translation performance. This method inspires the LLM to perceive domain information from the source text, which then serves as a helpful hint to guide the translation process. Despite being trained on a small dataset of four domains, our CoT fine-tune approach achieves notable enhancements in translation accuracy and domain robustness than traditional fine-tuning, as evidenced by an average 1.53 BLEU score increase in over 20 German$\rightarrow$English distinct out-of-domain tests.

Related papers

• Investigating the potential of Sparse Mixtures-of-Experts for multi-domain neural machine translation [59.41178047749177]
  We focus on multi-domain Neural Machine Translation, with the goal of developing efficient models which can handle data from various domains seen during training and are robust to domains unseen during training. We hypothesize that Sparse Mixture-of-Experts (SMoE) models are a good fit for this task, as they enable efficient model scaling. We conduct a series of experiments aimed at validating the utility of SMoE for the multi-domain scenario, and find that a straightforward width scaling of Transformer is a simpler and surprisingly more efficient approach in practice, and reaches the same performance level as SMoE.
  arXiv  Detail & Related papers  (2024-07-01T09:45:22Z)
• Fine-tuning Large Language Models for Domain-specific Machine Translation [8.439661191792897]
  Large language models (LLMs) have made significant progress in machine translation (MT) However, their potential in domain-specific MT remains under-explored. This paper proposes a prompt-oriented fine-tuning method, denoted as LlamaIT, to effectively and efficiently fine-tune a general-purpose LLM for domain-specific MT tasks.
  arXiv  Detail & Related papers  (2024-02-23T02:24:15Z)
• Domain Adaptation for Arabic Machine Translation: The Case of Financial Texts [0.7673339435080445]
  We develop a parallel corpus for Arabic-English (AR- EN) translation in the financial domain. We fine-tune several NMT and Large Language models including ChatGPT-3.5 Turbo. The quality of ChatGPT translation was superior than other models based on automatic and human evaluations.
  arXiv  Detail & Related papers  (2023-09-22T13:37:19Z)
• GP-UNIT: Generative Prior for Versatile Unsupervised Image-to-Image Translation [103.54337984566877]
  We introduce a novel versatile framework, Generative Prior-guided UNsupervised Image-to-image Translation (GP-UNIT) GP-UNIT is able to perform valid translations between both close domains and distant domains. We validate the superiority of GP-UNIT over state-of-the-art translation models in robust, high-quality and diversified translations.
  arXiv  Detail & Related papers  (2023-06-07T17:59:22Z)
• 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)
• Can Domains Be Transferred Across Languages in Multi-Domain Multilingual Neural Machine Translation? [52.27798071809941]
  This paper investigates whether the domain information can be transferred across languages on the composition of multi-domain and multilingual NMT. We find that multi-domain multilingual (MDML) NMT can boost zero-shot translation performance up to +10 gains on BLEU.
  arXiv  Detail & Related papers  (2022-10-20T23:13:54Z)
• Domain-Specific Text Generation for Machine Translation [7.803471587734353]
  We propose a novel approach to domain adaptation leveraging state-of-the-art pretrained language models (LMs) for domain-specific data augmentation. We employ mixed fine-tuning to train models that significantly improve translation of in-domain texts.
  arXiv  Detail & Related papers  (2022-08-11T16:22:16Z)
• Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation [61.27321597981737]
  $k$NN-MT has shown the promising capability of directly incorporating the pre-trained neural machine translation (NMT) model with domain-specific token-level $k$-nearest-neighbor retrieval. We propose a novel framework that directly uses in-domain monolingual sentences in the target language to construct an effective datastore for $k$-nearest-neighbor retrieval.
  arXiv  Detail & Related papers  (2021-09-14T11:50:01Z)
• Iterative Domain-Repaired Back-Translation [50.32925322697343]
  In this paper, we focus on the domain-specific translation with low resources, where in-domain parallel corpora are scarce or nonexistent. We propose a novel iterative domain-repaired back-translation framework, which introduces the Domain-Repair model to refine translations in synthetic bilingual data. Experiments on adapting NMT models between specific domains and from the general domain to specific domains demonstrate the effectiveness of our proposed approach.
  arXiv  Detail & Related papers  (2020-10-06T04:38:09Z)

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.