Related papers: In-Domain African Languages Translation Using LLMs and Multi-armed Bandits

In-Domain African Languages Translation Using LLMs and Multi-armed Bandits

URL: http://arxiv.org/abs/2505.15069v1
Date: Wed, 21 May 2025 03:33:27 GMT
Title: In-Domain African Languages Translation Using LLMs and Multi-armed Bandits
Authors: Pratik Rakesh Singh, Kritarth Prasad, Mohammadi Zaki, Pankaj Wasnik,
Abstract summary: We investigate strategies for selecting the most suitable NMT model for a given domain using bandit-based algorithms.<n>Our method effectively addresses the resource constraints by facilitating optimal model selection with high confidence.
Score: 3.2498796510544636
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Neural Machine Translation (NMT) systems face significant challenges when working with low-resource languages, particularly in domain adaptation tasks. These difficulties arise due to limited training data and suboptimal model generalization, As a result, selecting an optimal model for translation is crucial for achieving strong performance on in-domain data, particularly in scenarios where fine-tuning is not feasible or practical. In this paper, we investigate strategies for selecting the most suitable NMT model for a given domain using bandit-based algorithms, including Upper Confidence Bound, Linear UCB, Neural Linear Bandit, and Thompson Sampling. Our method effectively addresses the resource constraints by facilitating optimal model selection with high confidence. We evaluate the approach across three African languages and domains, demonstrating its robustness and effectiveness in both scenarios where target data is available and where it is absent.

Related papers

Improving Multilingual Math Reasoning for African Languages [49.27985213689457]
We conduct experiments to evaluate different combinations of data types (translated versus synthetically generated), training stages (pre-training versus post-training), and other model adaptation configurations.<n>Our experiments focuses on mathematical reasoning tasks, using the Llama 3.1 model family as our base model.
arXiv Detail & Related papers (2025-05-26T11:35:01Z)
Sample Efficient Preference Alignment in LLMs via Active Exploration [63.84454768573154]
We take advantage of the fact that one can often choose contexts at which to obtain human feedback to most efficiently identify a good policy.<n>We propose an active exploration algorithm to efficiently select the data and provide theoretical proof that it has a worst-case regret bound.<n>Our method outperforms the baselines with limited samples of human preferences on several language models and four real-world datasets.
arXiv Detail & Related papers (2023-12-01T00:54:02Z)
A Systematic Analysis of Vocabulary and BPE Settings for Optimal Fine-tuning of NMT: A Case Study of In-domain Translation [0.0]
The choice of vocabulary and SW tokenization has a significant impact on both training and fine-tuning an NMT model. In this work we compare different strategies for SW tokenization and vocabulary generation with the ultimate goal to uncover an optimal setting for fine-tuning a domain-specific model.
arXiv Detail & Related papers (2023-03-01T18:26:47Z)
Improving Pre-trained Language Model Fine-tuning with Noise Stability Regularization [94.4409074435894]
We propose a novel and effective fine-tuning framework, named Layerwise Noise Stability Regularization (LNSR) Specifically, we propose to inject the standard Gaussian noise and regularize hidden representations of the fine-tuned model. We demonstrate the advantages of the proposed method over other state-of-the-art algorithms including L2-SP, Mixout and SMART.
arXiv Detail & Related papers (2022-06-12T04:42:49Z)
Distributionally Robust Multilingual Machine Translation [94.51866646879337]
We propose a new learning objective for Multilingual neural machine translation (MNMT) based on distributionally robust optimization. We show how to practically optimize this objective for large translation corpora using an iterated best response scheme. Our method consistently outperforms strong baseline methods in terms of average and per-language performance under both many-to-one and one-to-many translation settings.
arXiv Detail & Related papers (2021-09-09T03:48:35Z)
Unsupervised Neural Machine Translation for Low-Resource Domains via Meta-Learning [27.86606560170401]
We present a novel meta-learning algorithm for unsupervised neural machine translation (UNMT) We train the model to adapt to another domain by utilizing only a small amount of training data. Our model surpasses a transfer learning-based approach by up to 2-4 BLEU scores.
arXiv Detail & Related papers (2020-10-18T17:54:13Z)
Improving Context Modeling in Neural Topic Segmentation [18.92944038749279]
We enhance a segmenter based on a hierarchical attention BiLSTM network to better model context. Our optimized segmenter outperforms SOTA approaches when trained and tested on three datasets.
arXiv Detail & Related papers (2020-10-07T03:40:49Z)
Dynamic Data Selection and Weighting for Iterative Back-Translation [116.14378571769045]
We propose a curriculum learning strategy for iterative back-translation models. We evaluate our models on domain adaptation, low-resource, and high-resource MT settings. Experimental results demonstrate that our methods achieve improvements of up to 1.8 BLEU points over competitive baselines.
arXiv Detail & Related papers (2020-04-07T19:49:58Z)
A Simple Baseline to Semi-Supervised Domain Adaptation for Machine Translation [73.3550140511458]
State-of-the-art neural machine translation (NMT) systems are data-hungry and perform poorly on new domains with no supervised data. We propose a simple but effect approach to the semi-supervised domain adaptation scenario of NMT. This approach iteratively trains a Transformer-based NMT model via three training objectives: language modeling, back-translation, and supervised translation.
arXiv Detail & Related papers (2020-01-22T16:42:06Z)

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