nlpaug 1.0.1

Natural language processing augmentation library for deep neural networks

nlpaug

This python library helps you with augmenting nlp for your machine learning projects. Visit this introduction to understand about Data Augmentation in NLP. Augmenter is the basic element of augmentation while Flow is a pipeline to orchestra multi augmenter together.

Features

• Generate synthetic data for improving model performance without manual effort
• Simple, easy-to-use and lightweight library. Augment data in 3 lines of code
• Plug and play to any machine leanring/ neural network frameworks (e.g. scikit-learn, PyTorch, TensorFlow)
• Support textual and audio input

Textual Data Augmentation Example

Acoustic Data Augmentation Example

Section	Description
Quick Demo	How to use this library
Augmenter	Introduce all available augmentation methods
Installation	How to install this library
Recent Changes	Latest enhancement
Extension Reading	More real life examples or researchs
Reference	Refernce of external resources such as data or model

Quick Demo

• Quick Example
• Example of Augmentation for Textual Inputs
• Example of Augmentation for Multilingual Textual Inputs
• Example of Augmentation for Spectrogram Inputs
• Example of Augmentation for Audio Inputs
• Example of Orchestra Multiple Augmenters
• Example of Showing Augmentation History
• How to train TF-IDF model
• How to create custom augmentation
• API Documentation

Augmenter

Augmenter	Target	Augmenter	Action	Description
Textual	Character	KeyboardAug	substitute	Simulate keyboard distance error
Textual		OcrAug	substitute	Simulate OCR engine error
Textual		RandomAug	insert, substitute, swap, delete	Apply augmentation randomly
Textual	Word	AntonymAug	substitute	Substitute opposite meaning word according to WordNet antonym
Textual		ContextualWordEmbsAug	insert, substitute	Feeding surroundings word to BERT, DistilBERT, RoBERTa or XLNet language model to find out the most suitlabe word for augmentation
Textual		RandomWordAug	swap, crop, delete	Apply augmentation randomly
Textual		SpellingAug	substitute	Substitute word according to spelling mistake dictionary
Textual		SplitAug	split	Split one word to two words randomly
Textual		SynonymAug	substitute	Substitute similar word according to WordNet/ PPDB synonym
Textual		TfIdfAug	insert, substitute	Use TF-IDF to find out how word should be augmented
Textual		WordEmbsAug	insert, substitute	Leverage word2vec, GloVe or fasttext embeddings to apply augmentation
Textual		BackTranslationAug	substitute	Leverage two translation models for augmentation
Textual	Sentence	ContextualWordEmbsForSentenceAug	insert	Insert sentence according to XLNet, GPT2 or DistilGPT2 prediction
Textual		AbstSummAug	substitute	Summarize article by abstractive summarization method
Signal	Audio	CropAug	delete	Delete audio's segment
Signal		LoudnessAug	substitute	Adjust audio's volume
Signal		MaskAug	substitute	Mask audio's segment
Signal		NoiseAug	substitute	Inject noise
Signal		PitchAug	substitute	Adjust audio's pitch
Signal		ShiftAug	substitute	Shift time dimension forward/ backward
Signal		SpeedAug	substitute	Adjust audio's speed
Signal		VtlpAug	substitute	Change vocal tract
Signal	Spectrogram	FrequencyMaskingAug	substitute	Set block of values to zero according to frequency dimension
Signal		TimeMaskingAug	substitute	Set block of values to zero according to time dimension
Signal		LoudnessAug	substitute	Adjust volume

Flow

Augmenter	Augmenter	Description
Pipeline	Sequential	Apply list of augmentation functions sequentially
Pipeline	Sometimes	Apply some augmentation functions randomly

Installation

The library supports python 3.5+ in linux and window platform.

To install the library:

pip install numpy requests nlpaug

or install the latest version (include BETA features) from github directly

pip install numpy git+https://github.com/makcedward/nlpaug.git

or install over conda

conda install -c makcedward nlpaug

If you use ContextualWordEmbsAug, ContextualWordEmbsForSentenceAug and AbstSummAug, install the following dependencies as well

pip install torch>=1.6.0 transformers>=3.0.2

If you use BackTranslationAug, install the following dependencies as well

pip install torch>=1.6.0 fairseq>=0.9.0

If you use AntonymAug, SynonymAug, install the following dependencies as well

pip install nltk>=3.4.5

If you use WordEmbsAug (word2vec, glove or fasttext), downloading pre-trained model first

from nlpaug.util.file.download import DownloadUtil
DownloadUtil.download_word2vec(dest_dir='.') # Download word2vec model
DownloadUtil.download_glove(model_name='glove.6B', dest_dir='.') # Download GloVe model
DownloadUtil.download_fasttext(model_name='wiki-news-300d-1M', dest_dir='.') # Download fasttext model

If you use SynonymAug (PPDB), downloading file from the following URI. You may not able to run the augmenter if you get PPDB file from other website

http://paraphrase.org/#/download

If you use PitchAug, SpeedAug and VtlpAug, install the following dependencies as well

pip install librosa>=0.7.1 matplotlib

Recent Changes

1.0.1 Sep 25, 2020

• Added Spectrogram's Loudness augmenter #156

1.0.0 Sep 24, 2020

• Upgraded to use AutoModel and AutoTokeizer for ContextualWordEmbsAug, ContextualWordEmbsForSentenceAug and AbstSummAug. Fix #133, #105
• Refactoring audio and spectrogram augmenters
• Added LoudnessAug into spectrogram augmenters
• Support single forward data input for deep learning models (i.e. ContextualWordEmbsAug, BackTranslationAug, ContextualWordEmbsForSentenceAug, AbstSummAug). #146
• Fix missing re-assing model paramters (e.g. device) for deep learning model
• BackTranslation supports to load model from local #149
• Fix device parameter bug #150
• Deprecated include_detail feature

See changelog for more details.

Extension Reading

• Data Augmentation library for Text
• Does your NLP model able to prevent adversarial attack?
• How does Data Noising Help to Improve your NLP Model?
• Data Augmentation library for Speech Recognition
• Data Augmentation library for Audio
• Unsupervied Data Augmentation
• A Visual Survey of Data Augmentation in NLP

Reference

This library uses data (e.g. capturing from internet), research (e.g. following augmenter idea), model (e.g. using pre-trained model) See data source for more details.

Citing

@misc{ma2019nlpaug,
  title={NLP Augmentation},
  author={Edward Ma},
  howpublished={https://github.com/makcedward/nlpaug},
  year={2019}
}

Book cited nlpaug

• S. Vajjala, B. Majumder, A. Gupta and H. Surana. Practical Natural Language Processing: A Comprehensive Guide to Building Real-World NLP Systems. 2020

Research paper cited nlpaug

• M. Raghu and E. Schmidt. A Survey of Deep Learning for Scientific Discovery. 2020
• H. Guan, J. Li, H. Xu and M. Devarakonda. Robustly Pre-trained Neural Model for Direct Temporal Relation Extraction. 2020
• X. He, K. Zhao and X. Chu. AutoML: A Survey of the State-of-the-Art. 2020
• S. Illium, R. Muller, A. Sedlmeier and C. Linnhoff-Popien. Surgical Mask Detection with Convolutional Neural Networks and Data Augmentations on Spectrograms. 2020
• D. Niederhut. A Python package for text data enrichment. 2020
• P. Ryan, S. Takafuji, C. Yang, N. Wilson and C. McBride. Using Self-Supervised Learning of Birdsong for Downstream Industrial Audio Classification. 2020
• Z. Shao, J. Yang and S. Ren. Calibrating Deep Neural Network Classifiers on Out-of-Distribution Datasets. 2020
• S. Qiu, B. Xu, J. Zhang, Y. Wang, X. Shen, G. D. Melo, C. Long and X. Li EasyAug: An Automatic Textual Data Augmentation Platform for Classification Tasks. 2020
• D. Nguyen, Q. H. Nguyen, M. Dao, D. Dang-Nguyen, C. Gurrin and B. T. Nguyen. Duplicate Identification Algorithms in SaaS Platforms. 2020
• A. Ollagnier and H. Williams. Text Augmentation Techniques for Clinical Case Classification. 2020
• V. Atliha and D. Šešok. Text Augmentation Using BERT for Image Captioning. 2020
• Y. Ma, X. Xu, and Y. Li. LungRN+NL: An Improved Adventitious Lung Sound Classification Using non-local block ResNet Neural Network with Mixup Data Augmentation. 2020
• S. N. Zisad, M. Shahadat and K. Andersson. Speech emotion recognition in neurological disorders using Convolutional Neural Network. 2020

Project cited nlpaug

• D. Garcia-Olano and A. Jain. Generating Counterfactual Explanations using Reinforcement Learning Methods for Tabular and Text data. 2019
• L. Yi. Avengers: Achieving Superhuman Performance for Question Answering on SQuAD 2.0 Using Multiple Data Augmentations, Randomized Mini-Batch Training and Architecture Ensembling. 2020

Contributions (Supporting Other Languages)

• sakares: Add Thai support to KeyboardAug