/ Natural Language Processing

An easy to use Natural Language Processing library and framework

An easy to use Natural Language Processing library and framework


An easy to use Natural Language Processing library and framework for predicting, training, fine-tuning, and serving up state-of-the-art NLP models.

AdaptNLP allows users ranging from beginner python coders to experienced machine learning engineers to leverage state-of-the-art NLP models and training techniques in one easy-to-use python package.

Built atop Zalando Research's Flair and Hugging Face's Transformers library, AdaptNLP provides Machine Learning Researchers and Scientists a modular and adaptive approach to a variety of NLP tasks with an Easy API for training, inference, and deploying NLP-based microservices.

Key Features

  • Full Guides and API Documentation
  • Tutorial Jupyter/Google Colab Notebooks
  • Unified API for NLP Tasks with SOTA Pretrained Models (Adaptable with Flair and Transformer's Models)
    • Token Tagging
    • Sequence Classification
    • Embeddings
    • Question Answering
    • More in development
  • Training and Fine-tuning Interface
    • Jeremy's ULM-FIT approach for transfer learning in NLP
    • Fine-tuning Transformer's language models and task-specific predictive heads like Flair's SequenceClassifier
  • Rapid NLP Model Deployment with Sebastián's FastAPI Framework
    • Containerized FastAPI app
    • Immediately deploy any custom trained Flair or AdaptNLP model
  • Dockerizing AdaptNLP with GPUs
    • Easily build and run AdaptNLP containers leveraging NVIDIA GPUs with Docker

Quick Start

Requirements and Installation

Virtual Environment

To avoid dependency clustering and issues, it would be wise to install AdaptNLP in a virtual environment.
To create a new python 3.6+ virtual environment, run this command and then activate it however your operating
system specifies:

python -m venv venv-adaptnlp
AdaptNLP Install

Install using pip in your virtual environment:

pip install adaptnlp

Examples and General Use

Once you have installed AdaptNLP, here are a few examples of what you can run with AdaptNLP modules:

Named Entity Recognition with EasyTokenTagger
from adaptnlp import EasyTokenTagger

## Example Text
example_text = "Novetta's headquarters is located in Mclean, Virginia."

## Load the token tagger module and tag text with the NER model 
tagger = EasyTokenTagger()
sentences = tagger.tag_text(text=example_text, model_name_or_path="ner")

## Output tagged token span results in Flair's Sentence object model
for sentence in sentences:
    for entity in sentence.get_spans("ner"):

English Sentiment Classifier EasySequenceClassifier
from adaptnlp import EasySequenceClassifier 

## Example Text
example_text = "Novetta is a great company that was chosen as one of top 50 great places to work!"

## Load the sequence classifier module and classify sequence of text with the english sentiment model 
classifier = EasySequenceClassifier()
sentences = classifier.tag_text(text=example_text, model_name_or_path="en-sentiment")

## Output labeled text results in Flair's Sentence object model
for sentence in sentences:

Span-based Question Answering EasyQuestionAnswering
from adaptnlp import EasyQuestionAnswering 

## Example Query and Context 
query = "What is the meaning of life?"
context = "Machine Learning is the meaning of life."
top_n = 5

## Load the QA module and run inference on results 
qa = EasyQuestionAnswering()
best_answer, best_n_answers = qa.predict_qa(query=query, context=context, n_best_size=top_n)

## Output top answer as well as top 5 answers
Sequence Classification Training SequenceClassifier
from adaptnlp import EasyDocumentEmbeddings, SequenceClassifierTrainer 

# Specify corpus data directory and model output directory
corpus = "Path/to/data/directory" 
OUTPUT_DIR = "Path/to/output/directory" 

# Instantiate AdaptNLP easy document embeddings module, which can take in a variable number of embeddings to make `Stacked Embeddings`.  
# You may also use custom Transformers LM models by specifying the path the the language model
doc_embeddings = EasyDocumentEmbeddings(model_name_or_path="bert-base-cased", methods = ["rnn"])

# Instantiate Sequence Classifier Trainer by loading in the data, data column map, and embeddings as an encoder
sc_trainer = SequenceClassifierTrainer(corpus=corpus, encoder=doc_embeddings, column_name_map={0: "text", 1:"label"})

# Find Learning Rate
learning_rate = sc_trainer.find_learning_rate(output_dir=OUTPUT_DIR)

# Train Using Flair's Sequence Classification Head
sc_trainer.train(output_dir=OUTPUT_DIR, learning_rate=learning_rate, max_epochs=150)

# Predict text labels with the trained model using `EasySequenceClassifier`
from adaptnlp import EasySequenceClassifier
example_text = '''Where was the Queen's wedding held? '''
classifier = EasySequenceClassifier()
sentences = classifier.tag_text(example_text, model_name_or_path=OUTPUT_DIR / "final-model.pt")
print("Label output:\n")
for sentence in sentences:
Transformers Language Model Fine Tuning LMFineTuner
from adaptnlp import LMFineTuner

# Specify Text Data File Paths
train_data_file = "Path/to/train.csv"
eval_data_file = "Path/to/test.csv"

# Instantiate Finetuner with Desired Language Model
finetuner = LMFineTuner(train_data_file=train_data_file, eval_data_file=eval_data_file, model_type="bert", model_name_or_path="bert-base-cased")

# Find Optimal Learning Rate
learning_rate = finetuner.find_learning_rate(base_path="Path/to/base/directory")

# Train and Save Fine Tuned Language Models
finetuner.train_one_cycle(output_dir="Path/to/output/directory", learning_rate=learning_rate)


Look in the Tutorials directory for a quick introduction to the library and its very simple
and straight forward use cases:

  1. Token Classification: NER, POS, Chunk, and Frame Tagging
  2. Sequence Classification: Sentiment
  3. Embeddings: Transformer Embeddings e.g. BERT, XLM, GPT2, XLNet, roBERTa, ALBERT
  4. Question Answering: Span-based Question Answering Model
  5. Custom Fine-Tuning and Training with Transformer Models

Checkout the documentation for more information.

REST Service

We use FastAPI for standing up endpoints for serving state-of-the-art NLP models with AdaptNLP.

Swagger Example

The REST directory contains more detail on deploying a REST API locally or with docker in a very easy and
fast way.


AdaptNLP official docker images are up on Docker Hub.

Images have AdaptNLP installed from source in developer mode with tutorial notebooks available.

Images can build with GPU support if NVIDA-Docker is correctly installed.

Pull and Run AdaptNLP Immediately

Simply run an image with AdaptNLP installed from source in developer mode by running:

docker run -it --rm achangnovetta/adaptnlp:latest

Run an image with AdaptNLP running on GPUs if you have nvidia drivers and nvidia-docker 19.03+ installed:

docker run -it --rm --gpus all achangnovetta/adaptnlp:latest


Build docker image and run container with the following commands in the directory of the Dockerfile
to create a container with adaptnlp installed and ready to go

Note: A container with GPUs enabled requires Docker version 19.03+ and nvida-docker installed

docker build -t achangnovetta/adaptnlp:latest .
docker run -it --rm achangnovetta/adaptnlp:latest

If you want to use CUDA compatible GPUs

docker run -it --rm --gpus all achangnovetta/adaptnlp:latest