nlpaug 0.0.5

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.

• Data Augmentation library for Text
• Data Augmentation library for Speech Recognition
• Data Augmentation library for Audio

Starter Guides

• Augmentation for character and word
• Augmentation for spectrogram (audio input)
• Augmentation for audio
• How to create custom augmentation

Augmenter

Target	Augmenter	Action	Description
Character	RandomAug	Insert	Insert character randomly
		Substitute	Substitute character randomly
		Swap	Swap character randomly
		Delete	Delete character randomly
	OcrAug	Substitute	Simulate OCR engine error
	QwertyAug	Substitute	Simulate keyboard distnace error
Word	RandomWordAug	Swap	Swap word randomly
		Delete	Delete word randomly
	WordNetAug	Substitute	Substitute word according to WordNet's synonym
	Word2vecAug	Insert	Insert word randomly from word2vec dictionary
		Substitute	Substitute word based on word2vec embeddings
	GloVeAug	Insert	Insert word randomly from GloVe dictionary
		Substitute	Substitute word based on GloVe embeddings
	FasttextAug	Insert	Insert word randomly from fasttext dictionary
		Substitute	Substitute word based on fasttext embeddings
	BertAug	Insert	Insert word based by feeding surroundings word to BERT language model
		Substitute	Substitute word based by feeding surroundings word to BERT language model
Spectrogram	FrequencyMaskingAug	Substitute	Set block of values to zero according to frequency dimension
	TimeMaskingAug	Substitute	Set block of values to zero according to time dimension
Audio	NoiseAug	Substitute	Inject noise
	PitchAug	Substitute	Adjust pitch
	ShiftAug	Substitute	Shift time dimension forward/ backward
	SpeedAug	Substitute	Adjust speed of audio

Flow

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

Installation

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

To install the library:

pip install nlpaug

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

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

Download word2vec or GloVe files if you use Word2VecAug, GloVeAug or FasttextAug:

• word2vec(GoogleNews-vectors-negative300)
• GloVe(glove.6B.50d)
• fasttext(wiki-news-300d-1M.vec.zip)

Recent Changes

0.0.5 Jul 2, 2019:

• Fixed #3, #4, #5, #7, Fixed #10

0.0.4 Jun 7, 2019:

• Added stopwords feature in character and word augmenter.
• Added character's swap augmenter.
• Added word's swap augmenter.
• Added validation rule for #1.
• Fixed BERT reverse tokenization for #2.

0.0.3 May 23, 2019:

• Added Speed, Noise, Shift and Pitch augmenters for Audio

0.0.2 Apr 30, 2019:

• Added Frequency Masking and Time Masking for Speech Recognition (Spectrogram).
• Added librosa library dependency for converting wav to spectrogram.

0.0.1 Mar 20, 2019: Project initialization

Test

Word2vec and GloVe models are used in word insertion and substitution. Those model files are necessary in order to run test case. You have to add ".env" file in root directory and the content should be
    - MODEL_DIR={MODEL FILE PATH}

Folder structure of model should be
    -- root directory
        - glove.6B.50d.txt
        - GoogleNews-vectors-negative300.bin
        - wiki-news-300d-1M.vec

Research Reference

Augmenter	Research
RandomAug, QwertyAug	D. Pruthi, B. Dhingra and Z. C. Lipton. Combating Adversarial Misspellings with Robust Word Recognition. 2019
WordNetAug	X. Zhang, J. Zhao and Y. LeCun. Character-level Convolutional Networks for Text Classification. 2015
WordNetAug	S. Kobayashi. C. Coulombe. Text Data Augmentation Made Simple By Leveraging NLP Cloud APIs. 2018
Word2vecAug, GloVeAug, FasttextAug	W. Y. Wang and D. Yang. That’s So Annoying!!!: A Lexical and Frame-Semantic Embedding Based Data Augmentation Approach to Automatic Categorization of Annoying Behaviors using #petpeeve Tweets. 2015
BertAug	S. Kobayashi. Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relation. 2018
FrequencyMaskingAug, TimeMaskingAug	D. S. Park, W. Chan, Y. Zhang, C. C. Chiu, B. Zoph, E. D. Cubuk and Q. V. Le. SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition. 2019