Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translation

• URL: http://arxiv.org/abs/2503.04554v1
• Date: Thu, 06 Mar 2025 15:37:31 GMT
• Title: Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translation
• Authors: Armel Zebaze, Benoît Sagot, Rachel Bawden,
• Abstract summary: Machine Translation has been shown to benefit from in-context examples when they are semantically similar to the sentence to translate.<n>We propose a new LLM-based translation paradigm, compositional translation, to replace naive few-shot MT with similarity-based demonstrations.<n>Our intuition is that this approach should improve translation because these shorter phrases should be intrinsically easier to translate and easier to match with relevant examples.
• Score: 20.704153242284114
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The ability of generative large language models (LLMs) to perform in-context learning has given rise to a large body of research into how best to prompt models for various natural language processing tasks. Machine Translation (MT) has been shown to benefit from in-context examples, in particular when they are semantically similar to the sentence to translate. In this paper, we propose a new LLM-based translation paradigm, compositional translation, to replace naive few-shot MT with similarity-based demonstrations. An LLM is used to decompose a sentence into simpler phrases, and then to translate each phrase with the help of retrieved demonstrations. Finally, the LLM is prompted to translate the initial sentence with the help of the self-generated phrase-translation pairs. Our intuition is that this approach should improve translation because these shorter phrases should be intrinsically easier to translate and easier to match with relevant examples. This is especially beneficial in low-resource scenarios, and more generally whenever the selection pool is small or out of domain. We show that compositional translation boosts LLM translation performance on a wide range of popular MT benchmarks, including FLORES 200, NTREX 128 and TICO-19. Code and outputs are available at https://github.com/ArmelRandy/compositional-translation

Related papers

• Lost in Literalism: How Supervised Training Shapes Translationese in LLMs [51.04435855143767]
  Large language models (LLMs) have achieved remarkable success in machine translation.<n>However, translationese, characterized by overly literal and unnatural translations, remains a persistent challenge.<n>We introduce methods to mitigate these biases, including polishing golden references and filtering unnatural training instances.
  arXiv  Detail & Related papers  (2025-03-06T12:14:45Z)
• Understanding In-Context Machine Translation for Low-Resource Languages: A Case Study on Manchu [53.437954702561065]
  In-context machine translation (MT) with large language models (LLMs) is a promising approach for low-resource MT. This study systematically investigates how each resource and its quality affects the translation performance, with the Manchu language. Our results indicate that high-quality dictionaries and good parallel examples are very helpful, while grammars hardly help.
  arXiv  Detail & Related papers  (2025-02-17T14:53:49Z)
• Large Language Models for Persian $ \leftrightarrow $ English Idiom Translation [5.689194193929357]
  Large language models (LLMs) have shown superior capabilities in translating figurative language compared to neural machine translation (NMT) systems.<n>This paper introduces two parallel datasets of sentences containing idiomatic expressions for Persian$rightarrow$English and English$rightarrow$Persian translations.<n>We evaluate various open- and closed-source LLMs, NMT models, and their combinations.<n>Experiments reveal that Claude-3.5-Sonnet delivers outstanding results in both translation directions.
  arXiv  Detail & Related papers  (2024-12-13T09:29:27Z)
• Language Models and Cycle Consistency for Self-Reflective Machine Translation [1.79487674052027]
  We generate multiple translation candidates from a source language A to a target language B, and subsequently translate these candidates back to the original language A. By evaluating the cycle consistency between the original and back-translated sentences using metrics such as token-level precision and accuracy, we implicitly estimate the translation quality in language B. For each source sentence, we identify the translation candidate with optimal cycle consistency with the original sentence as the final answer.
  arXiv  Detail & Related papers  (2024-11-05T04:01:41Z)
• Analyzing Context Contributions in LLM-based Machine Translation [21.95318929582271]
  Large language models (LLMs) have achieved state-of-the-art performance in machine translation (MT) We study how LLMs use various context parts, such as few-shot examples and the source text, when generating translations. Our findings shed light on the internal workings of LLM-based MT which go beyond those known for standard encoder-decoder MT models.
  arXiv  Detail & Related papers  (2024-10-21T17:51:41Z)
• IntGrad MT: Eliciting LLMs' Machine Translation Capabilities with Sentence Interpolation and Gradual MT [5.323504404265276]
  Large Language Models (LLMs) have demonstrated strong performance in translation without needing to be finetuned on additional parallel corpora. Previous works have focused on mitigating this issue by leveraging relevant few-shot examples or external resources such as dictionaries or grammar books. We propose a novel method named IntGrad MT that focuses on fully exploiting an LLM's inherent translation capability.
  arXiv  Detail & Related papers  (2024-10-15T15:26:28Z)
• Building Accurate Translation-Tailored LLMs with Language Aware Instruction Tuning [57.323716555996114]
  Off-target translation remains an unsolved problem, especially for low-resource languages. Recent works have either designed advanced prompting strategies to highlight the functionality of translation instructions or exploited the in-context learning ability of LLMs. In this work, we design a two-stage fine-tuning algorithm to improve the instruction-following ability (especially the translation direction) of LLMs.
  arXiv  Detail & Related papers  (2024-03-21T13:47:40Z)
• Speech Translation with Large Language Models: An Industrial Practice [64.5419534101104]
  We introduce LLM-ST, a novel and effective speech translation model constructed upon a pre-trained large language model (LLM) By integrating the large language model (LLM) with a speech encoder and employing multi-task instruction tuning, LLM-ST can produce accurate timestamped transcriptions and translations. Through rigorous experimentation on English and Chinese datasets, we showcase the exceptional performance of LLM-ST.
  arXiv  Detail & Related papers  (2023-12-21T05:32:49Z)
• 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)
• Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis [103.89753784762445]
  Large language models (LLMs) have demonstrated remarkable potential in handling multilingual machine translation (MMT) This paper systematically investigates the advantages and challenges of LLMs for MMT. We thoroughly evaluate eight popular LLMs, including ChatGPT and GPT-4.
  arXiv  Detail & Related papers  (2023-04-10T15:51:30Z)

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.