paper-with-me

홈 › Papers

Isotropic Contextual Representations through Variational Regularization

2021-09-29 · Cornelia Ferner, Stefan Wegenkittl

Contextual language representations achieve state-of-the-art performance across various natural language processing tasks. However, these representations have been shown to suffer from the degeneration problem, i.e. they occupy a narrow cone in the latent space. This problem can be addressed by enforcing isotropy in the latent space. In analogy to variational autoencoders, we suggest applying a token-level variational loss to a Transformer architecture and introduce the prior distribution's standard deviation as model parameter to optimize isotropy. The encoder-decoder architecture allows for learning interpretable embeddings that can be decoded into text again. Extracted features at sentence-level achieve competitive results on benchmark classification tasks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderSentence

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
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 $x$…
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…
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…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Stable Anisotropic Regularization

2023-05-30 · William Rudman, Carsten Eickhoff

Given the success of Large Language Models (LLMs), there has been considerable interest in studying the properties of model activations. The literature overwhelmingly agrees that LLM representations are dominated by a fe…

Space-adaptive anisotropic bivariate Laplacian regularization for image restoration

2019-08-02 · Luca Calatroni, Alessandro Lanza, Monica Pragliola, Fiorella Sgallari

In this paper we present a new regularization term for variational image restoration which can be regarded as a space-variant anisotropic extension of the classical isotropic Total Variation (TV) regularizer. The propose…

Image Restoration

Low Anisotropy Sense Retrofitting (LASeR) : Towards Isotropic and Sense Enriched Representations

2021-04-22 · NAACL (DeeLIO) 2021 6 · Geetanjali Bihani, Julia Taylor Rayz

Contextual word representation models have shown massive improvements on a multitude of NLP tasks, yet their word sense disambiguation capabilities remain poorly explained. To address this gap, we assess whether contextu…

Word Sense Disambiguation

Variational Depth Superresolution Using Example-Based Edge Representations

2015-12-01 · ICCV 2015 12 · David Ferstl, Matthias Ruther, Horst Bischof

In this paper we propose a novel method for depth image superresolution which combines recent advances in example based upsampling with variational superresolution based on a known blur kernel. Most traditional depth sup…

MIC: Maximizing Informational Capacity in Adaptive Representations via Isotropic Subspace Alignment

2026-05-28 · Dang Nguyen Hong, Nhi Ngoc-Yen Nguyen, Huy-Hieu Pham arxiv

Although multi-scales representation learning enables elastic-dimension embeddings, nested subspaces often suffer from dimensional redundancy and spectral collapse. To address this, we introduce MIC, a framework that opt…

Representation Learning