paper-with-me

Papers

Kernelized Bayesian Softmax for Text Generation

2019-11-01 · NeurIPS 2019 12 · Ning Miao, Hao Zhou, Chengqi Zhao, Wenxian Shi, Lei LI

Neural models for text generation require a softmax layer with proper token embeddings during the decoding phase. Most existing approaches adopt single point embedding for each token. However, a word may have multiple senses according to different context, some of which might be distinct. In this paper, we propose KerBS, a novel approach for learning better embeddings for text generation. KerBS embodies two advantages: (a) it employs a Bayesian composition of embeddings for words with multiple senses; (b) it is adaptive to semantic variances of words and robust to rare sentence context by imposing learned kernels to capture the closeness of words (senses) in the embedding space. Empirical studies show that KerBS significantly boosts the performance of several text generation tasks.

📄 PDF Abstract BibTeX arXiv:1911.00274

Code (1)

NingMiao/KerBS 공식 구현 tf

Tasks

SentenceText Generation

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Kernelized Classification in Deep Networks

2020-12-08 · Sadeep Jayasumana, Srikumar Ramalingam, Sanjiv Kumar

We propose a kernelized classification layer for deep networks. Although conventional deep networks introduce an abundance of nonlinearity for representation (feature) learning, they almost universally use a linear class…

ClassificationGeneral Classification

Revisiting Logistic-softmax Likelihood in Bayesian Meta-Learning for Few-Shot Classification

2023-10-16 · NeurIPS 2023 11 · Tianjun Ke, Haoqun Cao, Zenan Ling, Feng Zhou

Meta-learning has demonstrated promising results in few-shot classification (FSC) by learning to solve new problems using prior knowledge. Bayesian methods are effective at characterizing uncertainty in FSC, which is cru…

Data AugmentationMeta-Learning

Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding

2021-06-23 · NeurIPS 2021 12 · Shengjie Luo, Shanda Li, Tianle Cai, Di He 외

The attention module, which is a crucial component in Transformer, cannot scale efficiently to long sequences due to its quadratic complexity. Many works focus on approximating the dot-then-exponentiate softmax function …

Transformers Can Implement Preconditioned Richardson Iteration for In-Context Gaussian Kernel Regression

2026-05-08 · Mingsong Yan, Dongyang Li, Charles Kulick, Sui Tang arxiv

Mechanistic accounts of in-context learning (ICL) have identified iterative algorithms for linear regression and related linear prediction tasks, often using linear or ReLU attention variants. For nonlinear ICL, prior wo…

Bayesian Sparse Factor Analysis with Kernelized Observations

2020-06-01 · Carlos Sevilla-Salcedo, Alejandro Guerrero-López, Pablo M. Olmos, Vanessa Gómez-Verdejo

Multi-view problems can be faced with latent variable models since they are able to find low-dimensional projections that fairly capture the correlations among the multiple views that characterise each datum. On the othe…

feature selectionGaussian ProcessesMULTI-VIEW LEARNING