paper-with-me

Papers

Language Modeling with a General Second-Order RNN

2020-05-01 · LREC 2020 5 · Diego Maupom{\'e}, Marie-Jean Meurs

Different Recurrent Neural Network (RNN) architectures update their state in different manners as the input sequence is processed. RNNs including a multiplicative interaction between their current state and the current input, second-order ones, show promising performance in language modeling. In this paper, we introduce a second-order RNNs that generalizes existing ones. Evaluating on the Penn Treebank dataset, we analyze how its different components affect its performance in character-lever recurrent language modeling. We perform our experiments controlling the parameter counts of models. We find that removing the first-order terms does not hinder performance. We perform further experiments comparing the effects of the relative size of the state space and the multiplicative interaction space on performance. Our expectation was that a larger states would benefit language models built on longer documents, and larger multiplicative interaction states would benefit ones built on larger input spaces. However, our results suggest that this is not the case and the optimal relative size is the same for both document tokenizations used.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Multiplicative Models for Recurrent Language Modeling

2019-06-30 · Diego Maupomé, Marie-Jean Meurs

Recently, there has been interest in multiplicative recurrent neural networks for language modeling. Indeed, simple Recurrent Neural Networks (RNNs) encounter difficulties recovering from past mistakes when generating se…

Language ModelingLanguage Modelling

AdaFisher: Adaptive Second Order Optimization via Fisher Information

2024-05-26 · Damien Martins Gomes, Yanlei Zhang, Eugene Belilovsky, Guy Wolf 외

First-order optimization methods are currently the mainstream in training deep neural networks (DNNs). Optimizers like Adam incorporate limited curvature information by employing the diagonal matrix preconditioning of th…

Computational Efficiencyimage-classificationImage ClassificationLanguage Modeling+1

Towards Practical Second-Order Optimizers in Deep Learning: Insights from Fisher Information Analysis

2025-04-26 · Damien Martins Gomes

First-order optimization methods remain the standard for training deep neural networks (DNNs). Optimizers like Adam incorporate limited curvature information by preconditioning the stochastic gradient with a diagonal mat…

Computational Efficiencyimage-classificationImage ClassificationLanguage Modeling+2

Modeling Label Correlations for Second-Order Semantic Dependency Parsing with Mean-Field Inference

2022-04-07 · Songlin Yang, Kewei Tu

Second-order semantic parsing with end-to-end mean-field inference has been shown good performance. In this work we aim to improve this method by modeling label correlations between adjacent arcs. However, direct modelin…

Dependency ParsingSemantic Dependency ParsingSemantic ParsingSentence+1

General Backpropagation Algorithm for Training Second-order Neural Networks

2017-08-17 · Fenglei Fan, Wenxiang Cong, Ge Wang

The artificial neural network is a popular framework in machine learning. To empower individual neurons, we recently suggested that the current type of neurons could be upgraded to 2nd order counterparts, in which the li…

BIG-bench Machine Learning