paper-with-me

홈 › Papers

CULL-MT: Compression Using Language and Layer pruning for Machine Translation

2024-11-10 · Pedram Rostami, Mohammad Javad Dousti

Multilingual machine translation models often outperform traditional bilingual models by leveraging translation knowledge transfer. Recent advancements have led to these models supporting hundreds of languages and achieving state-of-the-art results across various translation directions. However, as these models grow larger, their inference operations become increasingly costly. In many use cases, there is no need to support such a wide range of language pairs, as translation is typically needed in only a few selected directions. In this paper, we present CULL-MT, a compression method for machine translation models based on structural layer pruning and selected language directions. Our approach identifies and prunes unimportant layers using a greedy strategy, then mitigates the impact by applying knowledge distillation from the original model along with parameter-efficient fine-tuning. We apply CULL-MT to the NLLB-3.3B and LLaMA3.1-8B-Instruct models. In a multi-way translation scenario (Persian, French, and German to English), we find the NLLB-3.3B model to be robust, allowing 25% of layers to be pruned with only a 0.9 spBLEU drop. However, LLaMA3.1-8B-Instruct is more sensitive, with a 2.0 spBLEU drop after pruning 5 layers.

📄 PDF Abstract BibTeX arXiv:2411.06506

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationMachine Translationparameter-efficient fine-tuningTransfer LearningTranslation

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Iterative Layer Pruning for Efficient Translation Inference

2025-10-26 · Yasmin Moslem, Muhammad Hazim Al Farouq, John D. Kelleher arxiv

Large language models (LLMs) have transformed many areas of natural language processing, including machine translation. However, efficient deployment of LLMs remains challenging due to their intensive computational requi…

Machine TranslationModel Compression

Structural Anchor Pruning: Training-Free Multi-Vector Compression for Visual Document Retrieval

2026-01-27 · Zhuchenyang Liu, Ziyu Hu, Yao Zhang, Yu Xiao arxiv

Recent Vision-Language Models (e.g., ColPali) enable fine-grained Visual Document Retrieval (VDR) but incur prohibitive multi-vector index storage overhead. Existing training-free pruning methods either rely on heuristic…

Just CHOP: Embarrassingly Simple LLM Compression

2023-05-24 · Ananya Harsh Jha, Tom Sherborne, Evan Pete Walsh, Dirk Groeneveld 외

Large language models (LLMs) enable unparalleled few- and zero-shot reasoning capabilities but at a high computational footprint. A growing assortment of methods for compression promises to reduce the computational burde…

Knowledge DistillationLanguage ModelingLanguage ModellingLarge Language Model+1

Effective Layer Pruning Through Similarity Metric Perspective

2024-05-27 · Ian Pons, Bruno Yamamoto, Anna H. Reali Costa, Artur Jordao

Deep neural networks have been the predominant paradigm in machine learning for solving cognitive tasks. Such models, however, are restricted by a high computational overhead, limiting their applicability and hindering a…

Towards Optimal Compression: Joint Pruning and Quantization

2023-02-15 · Ben Zandonati, Glenn Bucagu, Adrian Alan Pol, Maurizio Pierini 외

Model compression is instrumental in optimizing deep neural network inference on resource-constrained hardware. The prevailing methods for network compression, namely quantization and pruning, have been shown to enhance …

Model CompressionNeural Architecture SearchQuantization