paper-with-me

홈 › Papers

Language Through a Prism: A Spectral Approach for Multiscale Language Representations

2020-11-09 · NeurIPS 2020 12 · Alex Tamkin, Dan Jurafsky, Noah Goodman

Language exhibits structure at different scales, ranging from subwords to words, sentences, paragraphs, and documents. To what extent do deep models capture information at these scales, and can we force them to better capture structure across this hierarchy? We approach this question by focusing on individual neurons, analyzing the behavior of their activations at different timescales. We show that signal processing provides a natural framework for separating structure across scales, enabling us to 1) disentangle scale-specific information in existing embeddings and 2) train models to learn more about particular scales. Concretely, we apply spectral filters to the activations of a neuron across an input, producing filtered embeddings that perform well on part of speech tagging (word-level), dialog speech acts classification (utterance-level), or topic classification (document-level), while performing poorly on the other tasks. We also present a prism layer for training models, which uses spectral filters to constrain different neurons to model structure at different scales. Our proposed BERT + Prism model can better predict masked tokens using long-range context and produces multiscale representations that perform better at utterance- and document-level tasks. Our methods are general and readily applicable to other domains besides language, such as images, audio, and video.

📄 PDF Abstract BibTeX arXiv:2011.04823

Code (1)

zh217/torch-dct pytorch

Tasks

Part-Of-Speech TaggingTopic Classification

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
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 $x$…
Multi-Head Attention 설명 없음
Residual Connection 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
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…

Similar Papers 제목 키워드 기반

PRISM: Periodic Representation with multIscale and Similarity graph Modelling for enhanced crystal structure property prediction

2025-11-25 · Àlex Solé, Albert Mosella-Montoro, Joan Cardona, Daniel Aravena 외 arxiv

Crystal structures are characterised by repeating atomic patterns within unit cells across three-dimensional space, posing unique challenges for graph-based representation learning. Current methods often overlook essenti…

Representation LearningGraph Neural Network

PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation

2026-05-22 · Junru Zhang, Lang Feng, Jinbo Wang, Xu Guo 외 arxiv

Generating high-quality time-series data is challenging because real-world signals often exhibit multimodal patterns and multiscale dynamics, including oscillations and high-frequency variations. Flow Matching (FM) offer…

PRISM: Structured Optimization via Anisotropic Spectral Shaping

2026-02-03 · Yujie Yang arxiv

We propose PRISM, an optimizer that enhances first-order spectral descent methods like Muon with partial second-order information. It constructs an efficient, low-rank quasi-second-order preconditioner via innovation-aug…

Prism: Spectral Parameter Sharing for Multi-Agent Reinforcement Learning

2026-02-06 · Kyungbeom Kim, Seungwon Oh, Kyung-Joong Kim arxiv

Parameter sharing is a key strategy in multi-agent reinforcement learning (MARL) for improving scalability, yet conventional fully shared architectures often collapse into homogeneous behaviors. Recent methods introduce …

Multi-agent Reinforcement Learning

PRISM: Deriving a White-Box Transformer as a Signal-Noise Decomposition Operator via Maximum Coding Rate Reduction

2026-01-21 · Dongchen Huang arxiv

Deep learning models, particularly Transformers, are often criticized as "black boxes" and lack interpretability. We propose Prism, a white-box attention-based architecture derived from the principles of Maximizing Codin…