MT-PATCHER: Selective and Extendable Knowledge Distillation from Large Language Models for Machine Translation

• URL: http://arxiv.org/abs/2403.09522v2
• Date: Mon, 1 Apr 2024 07:11:32 GMT
• Title: MT-PATCHER: Selective and Extendable Knowledge Distillation from Large Language Models for Machine Translation
• Authors: Jiahuan Li, Shanbo Cheng, Shujian Huang, Jiajun Chen,
• Abstract summary: Large Language Models (LLM) have demonstrated their strong ability in the field of machine translation (MT) We propose a framework called MT-Patcher, which transfers knowledge from LLMs to existing MT models in a selective, comprehensive and proactive manner.
• Score: 61.65537912700187
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLM) have demonstrated their strong ability in the field of machine translation (MT), yet they suffer from high computational cost and latency. Therefore, transferring translation knowledge from giant LLMs to medium-sized machine translation models is a promising research direction. However, traditional knowledge distillation methods do not take the capability of student and teacher models into consideration, therefore repeatedly teaching student models on the knowledge they have learned, and failing to extend to novel contexts and knowledge. In this paper, we propose a framework called MT-Patcher, which transfers knowledge from LLMs to existing MT models in a selective, comprehensive and proactive manner. Considering the current translation ability of student MT models, we only identify and correct their translation errors, instead of distilling the whole translation from the teacher. Leveraging the strong language abilities of LLMs, we instruct LLM teachers to synthesize diverse contexts and anticipate more potential errors for the student. Experiment results on translating both specific language phenomena and general MT benchmarks demonstrate that finetuning the student MT model on about 10% examples can achieve comparable results to the traditional knowledge distillation method, and synthesized potential errors and diverse contexts further improve translation performances on unseen contexts and words.

Related papers

• TasTe: Teaching Large Language Models to Translate through Self-Reflection [82.83958470745381]
  Large language models (LLMs) have exhibited remarkable performance in various natural language processing tasks. We propose the TasTe framework, which stands for translating through self-reflection. The evaluation results in four language directions on the WMT22 benchmark reveal the effectiveness of our approach compared to existing methods.
  arXiv  Detail & Related papers  (2024-06-12T17:21:21Z)
• Machine Translation with Large Language Models: Prompt Engineering for Persian, English, and Russian Directions [0.0]
  Generative large language models (LLMs) have demonstrated exceptional proficiency in various natural language processing (NLP) tasks. We conducted an investigation into two popular prompting methods and their combination, focusing on cross-language combinations of Persian, English, and Russian.
  arXiv  Detail & Related papers  (2024-01-16T15:16:34Z)
• On-the-Fly Fusion of Large Language Models and Machine Translation [3.718665608549311]
  We propose the on-the-fly ensembling of a machine translation model with an LLM prompted on the same task and input. We find that a slightly weaker-at-translation LLM can improve translations of a NMT model, and ensembling with an LLM can produce better translations than ensembling two stronger MT models.
  arXiv  Detail & Related papers  (2023-11-14T16:49:33Z)
• Towards Effective Disambiguation for Machine Translation with Large Language Models [65.80775710657672]
  We study the capabilities of large language models to translate "ambiguous sentences" Experiments show that our methods can match or outperform state-of-the-art systems such as DeepL and NLLB in four out of five language directions.
  arXiv  Detail & Related papers  (2023-09-20T22:22:52Z)
• TIM: Teaching Large Language Models to Translate with Comparison [78.66926087162672]
  We propose a novel framework using examples in comparison to teach LLMs to learn translation. Our approach involves presenting the model with examples of correct and incorrect translations and using a preference loss to guide the model's learning. Our findings offer a new perspective on fine-tuning LLMs for translation tasks and provide a promising solution for generating high-quality translations.
  arXiv  Detail & Related papers  (2023-07-10T08:15:40Z)
• Document-Level Machine Translation with Large Language Models [91.03359121149595]
  Large language models (LLMs) can produce coherent, cohesive, relevant, and fluent answers for various natural language processing (NLP) tasks. This paper provides an in-depth evaluation of LLMs' ability on discourse modeling.
  arXiv  Detail & Related papers  (2023-04-05T03:49:06Z)
• Self-Guided Curriculum Learning for Neural Machine Translation [25.870500301724128]
  We propose a self-guided curriculum strategy to encourage the learning of neural machine translation (NMT) models. Our approach can consistently improve translation performance against strong baseline Transformer.
  arXiv  Detail & Related papers  (2021-05-10T16:12:14Z)
• Assessing the Bilingual Knowledge Learned by Neural Machine Translation Models [72.56058378313963]
  We bridge the gap by assessing the bilingual knowledge learned by NMT models with phrase table. We find that NMT models learn patterns from simple to complex and distill essential bilingual knowledge from the training examples.
  arXiv  Detail & Related papers  (2020-04-28T03:44:34Z)

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.