aisolab / Nlp_classification
Licence: mit
Implementing nlp papers relevant to classification with PyTorch, gluonnlp
Stars: β 202
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Nlp classification
Artificial Adversary
π£οΈ Tool to generate adversarial text examples and test machine learning models against them
Stars: β 348 (+72.28%)
Mutual labels: classification, text-classification
Fake news detection
Fake News Detection in Python
Stars: β 194 (-3.96%)
Mutual labels: classification, text-classification
Rmdl
RMDL: Random Multimodel Deep Learning for Classification
Stars: β 375 (+85.64%)
Mutual labels: classification, text-classification
text2class
Multi-class text categorization using state-of-the-art pre-trained contextualized language models, e.g. BERT
Stars: β 15 (-92.57%)
Mutual labels: text-classification, classification
Applied Text Mining In Python
Repo for Applied Text Mining in Python (coursera) by University of Michigan
Stars: β 59 (-70.79%)
Mutual labels: classification, text-classification
support-tickets-classification
This case study shows how to create a model for text analysis and classification and deploy it as a web service in Azure cloud in order to automatically classify support tickets. This project is a proof of concept made by Microsoft (Commercial Software Engineering team) in collaboration with Endava http://endava.com/en
Stars: β 142 (-29.7%)
Mutual labels: text-classification, classification
Text classification
all kinds of text classification models and more with deep learning
Stars: β 7,179 (+3453.96%)
Mutual labels: classification, text-classification
Relation-Classification
Relation Classification - SEMEVAL 2010 task 8 dataset
Stars: β 46 (-77.23%)
Mutual labels: text-classification, classification
Textclassification
All kinds of neural text classifiers implemented by Keras
Stars: β 51 (-74.75%)
Mutual labels: classification, text-classification
Ml Classify Text Js
Machine learning based text classification in JavaScript using n-grams and cosine similarity
Stars: β 38 (-81.19%)
Mutual labels: classification, text-classification
nlp classification
Implementing nlp papers relevant to classification with PyTorch, gluonnlp
Stars: β 224 (+10.89%)
Mutual labels: text-classification, classification
Fastrtext
R wrapper for fastText
Stars: β 103 (-49.01%)
Mutual labels: classification, text-classification
ML4K-AI-Extension
Use machine learning in AppInventor, with easy training using text, images, or numbers through the Machine Learning for Kids website.
Stars: β 18 (-91.09%)
Mutual labels: text-classification, classification
Text Classification Cnn Rnn
CNN-RNNδΈζζζ¬εη±»οΌεΊδΊTensorFlow
Stars: β 3,613 (+1688.61%)
Mutual labels: classification, text-classification
COVID-19-Tweet-Classification-using-Roberta-and-Bert-Simple-Transformers
Rank 1 / 216
Stars: β 24 (-88.12%)
Mutual labels: text-classification, classification
Eda nlp
Data augmentation for NLP, presented at EMNLP 2019
Stars: β 902 (+346.53%)
Mutual labels: classification, text-classification
awesome-text-classification
Text classification meets word embeddings.
Stars: β 27 (-86.63%)
Mutual labels: text-classification, classification
Cnn Question Classification Keras
Chinese Question Classifier (Keras Implementation) on BQuLD
Stars: β 28 (-86.14%)
Mutual labels: classification, text-classification
Deep Atrous Cnn Sentiment
Deep-Atrous-CNN-Text-Network: End-to-end word level model for sentiment analysis and other text classifications
Stars: β 64 (-68.32%)
Mutual labels: classification, text-classification
Awesome Text Classification
Awesome-Text-Classification Projects,Papers,Tutorial .
Stars: β 158 (-21.78%)
Mutual labels: classification, text-classification
NLP paper implementation relevant to classification with PyTorch
The papers were implemented in using korean corpus
Prelimnary & Usage
- preliminary
pyenv virualenv 3.7.7 nlp
pyenv activate nlp
pip install -r requirements.txt
- Usage
python build_dataset.py
python build_vocab.py
python train.py # default training parameter
python evaluate.py # defatul evaluation parameter
Single sentence classification (sentiment classification task)
- Using the Naver sentiment movie corpus v1.0 (a.k.a.
nsmc
) - Configuration
-
conf/model/{type}.json
(e.g.type = ["sencnn", "charcnn",...]
) conf/dataset/nsmc.json
-
- Structure
# example: Convolutional_Neural_Networks_for_Sentence_Classification
βββ build_dataset.py
βββ build_vocab.py
βββ conf
β βββ dataset
β β βββ nsmc.json
β βββ model
β βββ sencnn.json
βββ evaluate.py
βββ experiments
β βββ sencnn
β βββ epochs_5_batch_size_256_learning_rate_0.001
βββ model
β βββ data.py
β βββ __init__.py
β βββ metric.py
β βββ net.py
β βββ ops.py
β βββ split.py
β βββ utils.py
βββ nsmc
β βββ ratings_test.txt
β βββ ratings_train.txt
β βββ test.txt
β βββ train.txt
β βββ validation.txt
β βββ vocab.pkl
βββ train.py
βββ utils.py
Model \ Accuracy | Train (120,000) | Validation (30,000) | Test (50,000) | Date |
---|---|---|---|---|
SenCNN | 91.95% | 86.54% | 85.84% | 20/05/30 |
CharCNN | 86.29% | 81.69% | 81.38% | 20/05/30 |
ConvRec | 86.23% | 82.93% | 82.43% | 20/05/30 |
VDCNN | 86.59% | 84.29% | 84.10% | 20/05/30 |
SAN | 90.71% | 86.70% | 86.37% | 20/05/30 |
ETRIBERT | 91.12% | 89.24% | 88.98% | 20/05/30 |
SKTBERT | 92.20% | 89.08% | 88.96% | 20/05/30 |
- [x] Convolutional Neural Networks for Sentence Classification (as SenCNN)
- [x] Character-level Convolutional Networks for Text Classification (as CharCNN)
- [x] Efficient Character-level Document Classification by Combining Convolution and Recurrent Layers (as ConvRec)
- [x] Very Deep Convolutional Networks for Text Classification (as VDCNN)
- [x] A Structured Self-attentive Sentence Embedding (as SAN)
- [x] BERT_single_sentence_classification (as ETRIBERT, SKTBERT)
Pairwise-text-classification (paraphrase detection task)
- Creating dataset from https://github.com/songys/Question_pair
- Configuration
-
conf/model/{type}.json
(e.g.type = ["siam", "san",...]
) conf/dataset/qpair.json
-
- Structure
# example: Siamese_recurrent_architectures_for_learning_sentence_similarity
βββ build_dataset.py
βββ build_vocab.py
βββ conf
β βββ dataset
β β βββ qpair.json
β βββ model
β βββ siam.json
βββ evaluate.py
βββ experiments
β βββ siam
β βββ epochs_5_batch_size_64_learning_rate_0.001
βββ model
β βββ data.py
β βββ __init__.py
β βββ metric.py
β βββ net.py
β βββ ops.py
β βββ split.py
β βββ utils.py
βββ qpair
β βββ kor_pair_test.csv
β βββ kor_pair_train.csv
β βββ test.txt
β βββ train.txt
β βββ validation.txt
β βββ vocab.pkl
βββ train.py
βββ utils.py
Model \ Accuracy | Train (6,136) | Validation (682) | Test (758) | Date |
---|---|---|---|---|
Siam | 93.00% | 83.13% | 83.64% | 20/05/30 |
SAN | 89.47% | 82.11% | 81.53% | 20/05/30 |
Stochastic | 89.26% | 82.69% | 80.07% | 20/05/30 |
ETRIBERT | 95.07% | 94.42% | 94.06% | 20/05/30 |
SKTBERT | 95.43% | 92.52% | 93.93% | 20/05/30 |
- [x] A Structured Self-attentive Sentence Embedding (as SAN)
- [x] Siamese recurrent architectures for learning sentence similarity (as Siam)
- [x] Stochastic Answer Networks for Natural Language Inference (as Stochastic)
- [x] BERT_pairwise_text_classification (as ETRIBERT, SKTBERT)
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].