paper-with-me

홈 › Papers

Can the Variation of Model Weights be used as a Criterion for Self-Paced Multilingual NMT?

2024-10-05 · Àlex R. Atrio, Alexis Allemann, Ljiljana Dolamic, Andrei Popescu-Belis

Many-to-one neural machine translation systems improve over one-to-one systems when training data is scarce. In this paper, we design and test a novel algorithm for selecting the language of minibatches when training such systems. The algorithm changes the language of the minibatch when the weights of the model do not evolve significantly, as measured by the smoothed KL divergence between all layers of the Transformer network. This algorithm outperforms the use of alternating monolingual batches, but not the use of shuffled batches, in terms of translation quality (measured with BLEU and COMET) and convergence speed.

📄 PDF Abstract BibTeX arXiv:2410.04147

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationNMTTranslation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Distributed Self-Paced Learning in Alternating Direction Method of Multipliers

2018-07-06 · Xuchao Zhang, Liang Zhao, Zhiqian Chen, Chang-Tien Lu

Self-paced learning (SPL) mimics the cognitive process of humans, who generally learn from easy samples to hard ones. One key issue in SPL is the training process required for each instance weight depends on the other sa…

Deep Self-Paced Learning for Person Re-Identification

2017-10-07 · Sanping Zhou, Jinjun Wang, Deyu Meng, Xiaomeng Xin 외

Person re-identification (Re-ID) usually suffers from noisy samples with background clutter and mutual occlusion, which makes it extremely difficult to distinguish different individuals across the disjoint camera views. …

Person Re-IdentificationTriplet

Robust Self-Paced Hashing for Cross-Modal Retrieval with Noisy Labels

2025-01-03 · Ruitao Pu, Yuan Sun, Yang Qin, Zhenwen Ren 외

Cross-modal hashing (CMH) has appeared as a popular technique for cross-modal retrieval due to its low storage cost and high computational efficiency in large-scale data. Most existing methods implicitly assume that mult…

Computational EfficiencyCross-Modal RetrievalRetrieval

Spatially Self-Paced Convolutional Networks for Change Detection in Heterogeneous Images

2021-05-10 · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2021 5 · Hao Li, Maoguo Gong, Mingyang Zhang, Yue Wu

Change detection in heterogeneous remote sensing images is a challenging problem because it is hard to make a direct comparison in the original observation spaces, and most methods rely on a set of manually labeled sampl…

Change Detection

Simple and Robust Loss Design for Multi-Label Learning with Missing Labels

2021-12-13 · Youcai Zhang, Yuhao Cheng, Xinyu Huang, Fei Wen 외

Multi-label learning in the presence of missing labels (MLML) is a challenging problem. Existing methods mainly focus on the design of network structures or training schemes, which increase the complexity of implementati…

image-classificationImage ClassificationMissing LabelsMulti-Label Image Classification+1