seqal 0.3.4

Sequence labeling active learning framework for Python

SeqAL

SeqAL is a sequence labeling active learning framework based on Flair.

Installation

SeqAL is available on PyPI:

pip install seqal

SeqAL officially supports Python 3.8+.

Usage

To understand what SeqAL can do, we first introduce the pool-based active learning cycle.

• Step 0: Prepare seed data (a small number of labeled data used for training)
• Step 1: Train the model with seed data
  • Step 2: Predict unlabeled data with the trained model
  • Step 3: Query informative samples based on predictions
  • Step 4: Annotator (Oracle) annotate the selected samples
  • Step 5: Input the new labeled samples to labeled dataset
  • Step 6: Retrain model
• Repeat step2~step6 until the f1 score of the model beyond the threshold or annotation budget is no left

SeqAL can cover all steps except step 0 and step 4. Because there is no 3rd part annotation tool, we can run below script to simulate the active learning cycle.

from flair.embeddings import WordEmbeddings

from seqal.active_learner import ActiveLearner
from seqal.datasets import ColumnCorpus, ColumnDataset
from seqal.samplers import LeastConfidenceSampler

# 1. get the corpus
columns = {0: "text", 1: "ner"}
data_folder = "./data/sample_bio"
corpus = ColumnCorpus(
    data_folder,
    columns,
    train_file="train_seed.txt",
    dev_file="dev.txt",
    test_file="test.txt",
)

# 2. tagger params
tagger_params = {}
tagger_params["tag_type"] = "ner"
tagger_params["hidden_size"] = 256
embeddings = WordEmbeddings("glove")
tagger_params["embeddings"] = embeddings
tagger_params["use_rnn"] = False

# 3. trainer params
trainer_params = {}
trainer_params["max_epochs"] = 1
trainer_params["mini_batch_size"] = 32
trainer_params["learning_rate"] = 0.1
trainer_params["patience"] = 5

# 4. setup active learner
sampler = LeastConfidenceSampler()
learner = ActiveLearner(corpus, sampler, tagger_params, trainer_params)

# 5. initialize active learner
learner.initialize(dir_path="output/init_train")

# 6. prepare data pool
pool_file = data_folder + "/labeled_data_pool.txt"
data_pool = ColumnDataset(pool_file, columns)
unlabeled_sentences = data_pool.sentences

# 7. query setup
query_number = 2
token_based = False
iterations = 5

# 8. iteration
for i in range(iterations):
    # 9. query unlabeled sentences
    queried_samples, unlabeled_sentences = learner.query(
        unlabeled_sentences, query_number, token_based=token_based, research_mode=True
    )

    # 10. retrain model, the queried_samples will be added to corpus.train
    learner.teach(queried_samples, dir_path=f"output/retrain_{i}")

When calling learner.query(), we set research_mode=True. This means that we simulate the active learning cycle. You can also find the script in examples/active_learning_cycle_research_mode.py. If you want to connect SeqAL with an annotation tool, you can see the script in examples/active_learning_cycle_annotation_mode.py.

Tutorials

We provide a set of quick tutorials to get you started with the library.

• Tutorials on Github Page
• Tutorials on Markown
  • Tutorial 1: Introduction
  • Tutorial 2: Prepare Corpus
  • Tutorial 3: Active Learner Setup
  • Tutorial 4: Prepare Data Pool
  • Tutorial 5: Research and Annotation Mode
  • Tutorial 6: Query Setup
  • Tutorial 7: Annotated Data
  • Tutorial 8: Stopper
  • Tutorial 9: Output Labeled Data
  • Tutorial 10: Performance Recorder
  • Tutorial 11: Multiple Language Support

Performance

Active learning algorithms achieve 97% performance of the best deep model trained on full data using only 30% of the training data on the CoNLL 2003 English dataset. The CPU model can decrease the time cost greatly only sacrificing a little performance.

See performance for more detail about performance and time cost.

Contributing

If you have suggestions for how SeqAL could be improved, or want to report a bug, open an issue! We'd love all and any contributions.

For more, check out the Contributing Guide.

Credits

• Cookiecutter
• browniebroke/cookiecutter-pypackage
• flairNLP/flair
• modal