paper-with-me

Papers

Learning What's Easy: Fully Differentiable Neural Easy-First Taggers

2017-09-01 · EMNLP 2017 9 · Andr{\'e} F. T. Martins, Julia Kreutzer

We introduce a novel neural easy-first decoder that learns to solve sequence tagging tasks in a flexible order. In contrast to previous easy-first decoders, our models are end-to-end differentiable. The decoder iteratively updates a {``}sketch{''} of the predictions over the sequence. At its core is an attention mechanism that controls which parts of the input are strategically the best to process next. We present a new constrained softmax transformation that ensures the same cumulative attention to every word, and show how to efficiently evaluate and backpropagate over it. Our models compare favourably to BILSTM taggers on three sequence tagging tasks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderImitation LearningNamed Entity Recognition (NER)Part-Of-Speech Tagging

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
BiLSTM A Bidirectional LSTM, or biLSTM, is a sequence processing model that consists of two LSTMs: one taking the input in a forward direction, and the other in a backwards…
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

Easy Batch Normalization

2022-07-18 · Arip Asadulaev, Alexander Panfilov, Andrey Filchenkov

It was shown that adversarial examples improve object recognition. But what about their opposite side, easy examples? Easy examples are samples that the machine learning model classifies correctly with high confidence. I…

Object Recognition

A fully differentiable framework for training proxy Exchange Correlation Functionals for periodic systems

2026-02-17 · Rakshit Kumar Singh, Aryan Amit Barsainyan, Bharath Ramsundar arxiv

Density Functional Theory (DFT) is widely used for first-principles simulations in chemistry and materials science, but its computational cost remains a key limitation for large systems. Motivated by recent advances in M…

A Simple Approach to Differentiable Rendering of SDFs

2024-05-14 · Zichen Wang, Xi Deng, Ziyi Zhang, Wenzel Jakob 외

We present a simple algorithm for differentiable rendering of surfaces represented by Signed Distance Fields (SDF), which makes it easy to integrate rendering into gradient-based optimization pipelines. To tackle visibil…

Inverse Rendering

RenderBender: A Survey on Adversarial Attacks Using Differentiable Rendering

2024-11-14 · Matthew Hull, Haoran Wang, Matthew Lau, Alec Helbling 외

Differentiable rendering techniques like Gaussian Splatting and Neural Radiance Fields have become powerful tools for generating high-fidelity models of 3D objects and scenes. Their ability to produce both physically pla…

Depth EstimationImage ClassificationInverse Renderingobject-detection+3

EasyConvPooling: Random Pooling with Easy Convolution for Accelerating Training and Testing

2018-06-05 · Jianzhong Sheng, Chuanbo Chen, Chenchen Fu, Chun Jason Xue

Convolution operations dominate the overall execution time of Convolutional Neural Networks (CNNs). This paper proposes an easy yet efficient technique for both Convolutional Neural Network training and testing. The conv…