Film review classification

Last update: Jan 21, 2022

Overview

Film review classification

Решение задачи классификации отзывов на фильмы на положительные и отрицательные с помощью рекуррентных нейронных сетей

1. Задача:

Для набора отзывов на фильмы из Internet Movie Database (IMDB) необходимо научиться классифицировать отзывы на положительные и отрицательные

2. Технологии:

Python 3
Pytorch
Numpy
Torchtext
Google Colab

3. Модель:

Embedding-слой для представления индексов в отзыве в качестве векторов
RNN/GRU-ячейки для обработки текста (рекуррентные нейронные сети)
Linear + SoftMax слои для классификации текста

4. Результаты:

Точность предсказаний (метрика accuracy): 86%

Film review classification

Related tags

Overview

Film review classification

Решение задачи классификации отзывов на фильмы на положительные и отрицательные с помощью рекуррентных нейронных сетей

1. Задача:

2. Технологии:

3. Модель:

4. Результаты:

Owner

Nikita Dukin

Cours d'Algorithmique Appliquée avec Python pour BTS SIO SISR

A framework for attentive explainable deep learning on tabular data

A fast poisson image editing implementation that can utilize multi-core CPU or GPU to handle a high-resolution image input.

Time Series Cross-Validation -- an extension for scikit-learn

“英特尔创新大师杯”深度学习挑战赛赛道3：CCKS2021中文NLP地址相关性任务

PyTorch implementation of "ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context" (INTERSPEECH 2020)

Implementation of Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning

Official code for "EagerMOT: 3D Multi-Object Tracking via Sensor Fusion" [ICRA 2021]

AI Toolkit for Healthcare Imaging

Repo for our ICML21 paper Unsupervised Learning of Visual 3D Keypoints for Control

Company clustering with K-means/GMM and visualization with PCA, t-SNE, using SSAN relation extraction

ALL Snow Removed: Single Image Desnowing Algorithm Using Hierarchical Dual-tree Complex Wavelet Representation and Contradict Channel Loss (HDCWNet)

Synthetic Humans for Action Recognition, IJCV 2021

A best practice for tensorflow project template architecture.

Intel® Neural Compressor is an open-source Python library running on Intel CPUs and GPUs

Hierarchical probabilistic 3D U-Net, with attention mechanisms (—𝘈𝘵𝘵𝘦𝘯𝘵𝘪𝘰𝘯 𝘜-𝘕𝘦𝘵, 𝘚𝘌𝘙𝘦𝘴𝘕𝘦𝘵) and a nested decoder structure with deep supervision (—𝘜𝘕𝘦𝘵++).

Using Machine Learning to Test Causal Hypotheses in Conjoint Analysis

The repository forked from NVlabs uses our data. (Differentiable rasterization applied to 3D model simplification tasks)

Out of Distribution Detection on Natural Adversarial Examples

Github Traffic Insights as Prometheus metrics.

Film review classification

Related tags

Overview

Film review classification

Решение задачи классификации отзывов на фильмы на положительные и отрицательные с помощью рекуррентных нейронных сетей

1. Задача:

2. Технологии:

3. Модель:

4. Результаты:

Owner

Nikita Dukin

Cours d'Algorithmique Appliquée avec Python pour BTS SIO SISR

A framework for attentive explainable deep learning on tabular data

A fast poisson image editing implementation that can utilize multi-core CPU or GPU to handle a high-resolution image input.

Time Series Cross-Validation -- an extension for scikit-learn

“英特尔创新大师杯”深度学习挑战赛 赛道3：CCKS2021中文NLP地址相关性任务

PyTorch implementation of "ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context" (INTERSPEECH 2020)

Implementation of Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning

Official code for "EagerMOT: 3D Multi-Object Tracking via Sensor Fusion" [ICRA 2021]

AI Toolkit for Healthcare Imaging

Repo for our ICML21 paper Unsupervised Learning of Visual 3D Keypoints for Control

Company clustering with K-means/GMM and visualization with PCA, t-SNE, using SSAN relation extraction

ALL Snow Removed: Single Image Desnowing Algorithm Using Hierarchical Dual-tree Complex Wavelet Representation and Contradict Channel Loss (HDCWNet)

Synthetic Humans for Action Recognition, IJCV 2021

A best practice for tensorflow project template architecture.

Intel® Neural Compressor is an open-source Python library running on Intel CPUs and GPUs

Hierarchical probabilistic 3D U-Net, with attention mechanisms (—𝘈𝘵𝘵𝘦𝘯𝘵𝘪𝘰𝘯 𝘜-𝘕𝘦𝘵, 𝘚𝘌𝘙𝘦𝘴𝘕𝘦𝘵) and a nested decoder structure with deep supervision (—𝘜𝘕𝘦𝘵++).

Using Machine Learning to Test Causal Hypotheses in Conjoint Analysis

The repository forked from NVlabs uses our data. (Differentiable rasterization applied to 3D model simplification tasks)

Out of Distribution Detection on Natural Adversarial Examples

Github Traffic Insights as Prometheus metrics.

“英特尔创新大师杯”深度学习挑战赛赛道3：CCKS2021中文NLP地址相关性任务