paper-with-me

홈 › Papers

Do all Roads Lead to Rome? Understanding the Role of Initialization in Iterative Back-Translation

2020-02-28 · Mikel Artetxe, Gorka Labaka, Noe Casas, Eneko Agirre

Back-translation provides a simple yet effective approach to exploit monolingual corpora in Neural Machine Translation (NMT). Its iterative variant, where two opposite NMT models are jointly trained by alternately using a synthetic parallel corpus generated by the reverse model, plays a central role in unsupervised machine translation. In order to start producing sound translations and provide a meaningful training signal to each other, existing approaches rely on either a separate machine translation system to warm up the iterative procedure, or some form of pre-training to initialize the weights of the model. In this paper, we analyze the role that such initialization plays in iterative back-translation. Is the behavior of the final system heavily dependent on it? Or does iterative back-translation converge to a similar solution given any reasonable initialization? Through a series of empirical experiments over a diverse set of warmup systems, we show that, although the quality of the initial system does affect final performance, its effect is relatively small, as iterative back-translation has a strong tendency to convergence to a similar solution. As such, the margin of improvement left for the initialization method is narrow, suggesting that future research should focus more on improving the iterative mechanism itself.

📄 PDF Abstract BibTeX arXiv:2002.12867

Code (0)

등록된 구현이 없습니다.

Tasks

AllMachine TranslationNMTTranslationUnsupervised Machine Translation

Similar Papers 제목 키워드 기반

Neuron Campaign for Initialization Guided by Information Bottleneck Theory

2021-08-14 · Haitao Mao, Xu Chen, Qiang Fu, Lun Du 외

Initialization plays a critical role in the training of deep neural networks (DNN). Existing initialization strategies mainly focus on stabilizing the training process to mitigate gradient vanish/explosion problems. Howe…

Understanding the Learning Dynamics of LoRA: A Gradient Flow Perspective on Low-Rank Adaptation in Matrix Factorization

2025-03-10 · Ziqing Xu, Hancheng Min, Lachlan Ewen MacDonald, Jinqi Luo 외

Despite the empirical success of Low-Rank Adaptation (LoRA) in fine-tuning pre-trained models, there is little theoretical understanding of how first-order methods with carefully crafted initialization adapt models to ne…

image-classificationImage Classification

LaNet: Real-time Lane Identification by Learning Road SurfaceCharacteristics from Accelerometer Data

2020-04-06 · Madhumitha Harishankar, Jun Han, Sai Vineeth Kalluru Srinivas, Faisal Alqarni 외

The resolution of GPS measurements, especially in urban areas, is insufficient for identifying a vehicle's lane. In this work, we develop a deep LSTM neural network model LaNet that determines the lane vehicles are on by…

ClassificationGeneral Classification

CarSpeedNet: A Deep Neural Network-based Car Speed Estimation from Smartphone Accelerometer

2024-01-15 · Barak Or

We introduce the CarSpeedNet, a deep learning model designed to estimate car speed using three-axis accelerometer data from smartphones. Using 13 hours of data collected from a smartphone in cars across various roads, Ca…

All Roads Lead to Rome: Graph-Based Confidence Estimation for Large Language Model Reasoning

2025-09-16 · Caiqi Zhang, Chang Shu, Ehsan Shareghi, Nigel Collier arxiv

Confidence estimation is essential for the reliable deployment of large language models (LLMs). Existing methods are primarily designed for factual QA tasks and often fail to generalize to reasoning tasks. To address thi…