ganeshjawahar / Mem_absa
Licence: mit
Aspect Based Sentiment Analysis using End-to-End Memory Networks
Stars: ✭ 189
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Mem absa
Machine Learning From Scratch
Succinct Machine Learning algorithm implementations from scratch in Python, solving real-world problems (Notebooks and Book). Examples of Logistic Regression, Linear Regression, Decision Trees, K-means clustering, Sentiment Analysis, Recommender Systems, Neural Networks and Reinforcement Learning.
Stars: ✭ 42 (-77.78%)
Mutual labels: classification, neural-networks, sentiment-analysis
textlytics
Text processing library for sentiment analysis and related tasks
Stars: ✭ 25 (-86.77%)
Mutual labels: sentiment-analysis, classification
XED
XED multilingual emotion datasets
Stars: ✭ 34 (-82.01%)
Mutual labels: sentiment-analysis, classification
Deep Learning For Hackers
Machine Learning tutorials with TensorFlow 2 and Keras in Python (Jupyter notebooks included) - (LSTMs, Hyperameter tuning, Data preprocessing, Bias-variance tradeoff, Anomaly Detection, Autoencoders, Time Series Forecasting, Object Detection, Sentiment Analysis, Intent Recognition with BERT)
Stars: ✭ 586 (+210.05%)
Mutual labels: neural-networks, sentiment-analysis
awesome-text-classification
Text classification meets word embeddings.
Stars: ✭ 27 (-85.71%)
Mutual labels: sentiment-analysis, classification
COVID-19-Tweet-Classification-using-Roberta-and-Bert-Simple-Transformers
Rank 1 / 216
Stars: ✭ 24 (-87.3%)
Mutual labels: sentiment-analysis, classification
Pywick
High-level batteries-included neural network training library for Pytorch
Stars: ✭ 320 (+69.31%)
Mutual labels: classification, neural-networks
DeepSentiPers
Repository for the experiments described in the paper named "DeepSentiPers: Novel Deep Learning Models Trained Over Proposed Augmented Persian Sentiment Corpus"
Stars: ✭ 17 (-91.01%)
Mutual labels: sentiment-analysis, classification
Deep Atrous Cnn Sentiment
Deep-Atrous-CNN-Text-Network: End-to-end word level model for sentiment analysis and other text classifications
Stars: ✭ 64 (-66.14%)
Mutual labels: classification, sentiment-analysis
Graph 2d cnn
Code and data for the paper 'Classifying Graphs as Images with Convolutional Neural Networks' (new title: 'Graph Classification with 2D Convolutional Neural Networks')
Stars: ✭ 67 (-64.55%)
Mutual labels: classification, neural-networks
Text Cnn Tensorflow
Convolutional Neural Networks for Sentence Classification(TextCNN) implements by TensorFlow
Stars: ✭ 232 (+22.75%)
Mutual labels: classification, sentiment-analysis
Paddlex
PaddlePaddle End-to-End Development Toolkit（『飞桨』深度学习全流程开发工具）
Stars: ✭ 3,399 (+1698.41%)
Mutual labels: classification, neural-networks
Darwinexlabs
Datasets, tools and more from Darwinex Labs - Prop Investing Arm & Quant Team @ Darwinex
Stars: ✭ 248 (+31.22%)
Mutual labels: neural-networks, sentiment-analysis
Aspect-Based-Sentiment-Analysis
A python program that implements Aspect Based Sentiment Analysis classification system for SemEval 2016 Dataset.
Stars: ✭ 57 (-69.84%)
Mutual labels: sentiment-analysis, classification
Tutorials
AI-related tutorials. Access any of them for free → https://towardsai.net/editorial
Stars: ✭ 204 (+7.94%)
Mutual labels: neural-networks, sentiment-analysis
Ml Classify Text Js
Machine learning based text classification in JavaScript using n-grams and cosine similarity
Stars: ✭ 38 (-79.89%)
Mutual labels: classification, sentiment-analysis
Kaggle Rsna
Deep Learning for Automatic Pneumonia Detection, RSNA challenge
Stars: ✭ 74 (-60.85%)
Mutual labels: classification, neural-networks
100daysofmlcode
My journey to learn and grow in the domain of Machine Learning and Artificial Intelligence by performing the #100DaysofMLCode Challenge.
Stars: ✭ 146 (-22.75%)
Mutual labels: classification, neural-networks
Neural Cryptography Tensorflow
Neural Networks that invent their own encryption 🔑
Stars: ✭ 181 (-4.23%)
Mutual labels: neural-networks
Datastories Semeval2017 Task4
Deep-learning model presented in "DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis".
Stars: ✭ 184 (-2.65%)
Mutual labels: sentiment-analysis
Aspect Level Sentiment Classification with Deep Memory Network
TensorFlow implementation of Tang et al.'s EMNLP 2016 work.
Problem Statement
Given a sentence and an aspect occurring in the sentence, this task aims at inferring the sentiment polarity (e.g. positive, negative, neutral) of the aspect.
Example
For example, in sentence ''great food but the service was dreadful!'', the sentiment polarity of aspect ''food'' is positive while the polarity of aspect ''service'' is negative.
Quick Start
Download the 300-dimensional pre-trained word vectors from Glove and save it in the 'data' folder as 'data/glove.6B.300d.txt'.
Train a model with 7 hops on the Laptop dataset.
python main.py --show True
Note this code requires TensorFlow, Future and Progress packages to be installed. As of now, the model might not replicate the performance shown in the original paper as the authors have not yet confirmed the optimal hyper-parameters for training the memory network.
Training options
-
edim: internal state dimension [300] -
lindim: linear part of the state [75] -
nhop: number of hops [7] -
batch_size: batch size to use during training [128] -
nepoch: number of epoch to use during training [100] -
init_lr: initial learning rate [0.01] -
init_hid: initial internal state value [0.1] -
init_std: weight initialization std [0.05] -
max_grad_norm: clip gradients to this norm [50] -
pretrain_file: pre-trained glove vectors file path [../data/glove.6B.300d.txt] -
train_data: train gold data set path [./data/Laptop_Train_v2.xml] or [./data/Restaurants_Train_v2.xml] -
test_data: test gold data set path [./data/Laptops_Test_Gold.xml] or [./data/Restaurants_Test_Gold.xml] -
show: print progress [False]
Performance - Laptop Dataset (todo)
| Model | In Paper | This Code |
|---|---|---|
| MemNet (1) | 67.66 | |
| MemNet (2) | 71.14 | |
| MemNet (3) | 71.74 | |
| MemNet (4) | 72.21 | |
| MemNet (5) | 71.89 | |
| MemNet (6) | 72.21 | |
| MemNet (7) | 72.37 | |
| MemNet (8) | 72.05 | |
| MemNet (9) | 72.21 |
Performance - Restaurant Dataset (todo)
| Model | In Paper | This Code |
|---|---|---|
| MemNet (1) | 76.10 | |
| MemNet (2) | 78.61 | |
| MemNet (3) | 79.06 | |
| MemNet (4) | 79.87 | |
| MemNet (5) | 80.14 | |
| MemNet (6) | 80.05 | |
| MemNet (7) | 80.32 | |
| MemNet (8) | 80.14 | |
| MemNet (9) | 80.95 |
Acknowledgements
- More than 80% of the code is borrowed from carpedm20.
- Using this code means you have read and accepted the copyrights set by the dataset providers.
Author
Licence
MIT
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].