• Search by Module
• Search by Words
• Search Projects

• Java
• Python
• JavaScript
• TypeScript
• C++
• Scala
• Blog

• MatchZoo-py-master
  • .github
    • ISSUE_TEMPLATE
      • bug-report.md
      • usage-question.md
      • feature-request.md
  • matchzoo
    • datasets
      • snli
        • load_data.py
        • __init__.py
      • embeddings
        • embed_word.txt
        • embed_10_glove.txt
        • embed_err.txt.gb2312
        • embed_10_word2vec.txt
        • __init__.py
        • load_fasttext_embedding.py
        • load_glove_embedding.py
      • quora_qp
        • load_data.py
        • __init__.py
      • toy
        • dev.csv
        • __init__.py
        • train.csv
        • test.csv
        • embedding.2d.txt
      • __init__.py
      • wiki_qa
        • load_data.py
        • __init__.py
    • utils
      • list_recursive_subclasses.py
      • tensor_type.py
      • parse.py
      • get_file.py
      • average_meter.py
      • one_hot.py
      • __init__.py
      • early_stopping.py
      • timer.py
    • trainers
      • __init__.py
      • trainer.py
    • auto
      • preparer
        • preparer.py
        • prepare.py
        • __init__.py
      • tuner
        • tune.py
        • tuner.py
        • __init__.py
      • __init__.py
    • version.py
    • models
      • duet.py
      • conv_knrm.py
      • knrm.py
      • arci.py
      • match_pyramid.py
      • parameter_readme_generator.py
      • drmmtks.py
      • arcii.py
      • bert.py
      • dssm.py
      • esim.py
      • match_srnn.py
      • README.rst
      • matchlstm.py
      • dense_baseline.py
      • drmm.py
      • diin.py
      • __init__.py
      • bimpm.py
      • hbmp.py
      • anmm.py
      • mvlstm.py
      • cdssm.py
    • dataloader
      • callbacks
        • padding.py
        • lambda_callback.py
        • ngram.py
        • __init__.py
        • histogram.py
      • dataloader_builder.py
      • dataloader.py
      • __init__.py
      • dataset.py
      • dataset_builder.py
    • losses
      • __init__.py
      • rank_cross_entropy_loss.py
      • rank_hinge_loss.py
    • data_pack
      • data_pack.py
      • __init__.py
      • pack.py
    • engine
      • base_callback.py
      • param.py
      • base_model.py
      • base_metric.py
      • base_task.py
      • hyper_spaces.py
      • __init__.py
      • base_preprocessor.py
      • param_table.py
    • tasks
      • ranking.py
      • classification.py
      • __init__.py
    • __init__.py
    • metrics
      • mean_average_precision.py
      • accuracy.py
      • cross_entropy.py
      • average_precision.py
      • normalized_discounted_cumulative_gain.py
      • __init__.py
      • mean_reciprocal_rank.py
      • discounted_cumulative_gain.py
      • precision.py
    • embedding
      • embedding.py
      • __init__.py
    • modules
      • stacked_brnn.py
      • spatial_gru.py
      • bert_module.py
      • gaussian_kernel.py
      • dense_net.py
      • attention.py
      • matching.py
      • dropout.py
      • semantic_composite.py
      • __init__.py
      • character_embedding.py
      • matching_tensor.py
    • preprocessors
      • naive_preprocessor.py
      • basic_preprocessor.py
      • bert_preprocessor.py
      • units
        • matching_histogram.py
        • stop_removal.py
        • lowercase.py
        • stemming.py
        • unit.py
        • ngram_letter.py
        • tokenize.py
        • character_index.py
        • truncated_length.py
        • frequency_filter.py
        • __init__.py
        • punc_removal.py
        • digit_removal.py
        • stateful_unit.py
        • lemmatization.py
        • vocabulary.py
        • word_hashing.py
        • word_exact_match.py
      • __init__.py
      • build_vocab_unit.py
      • build_unit_from_data_pack.py
      • chain_transform.py
  • Makefile
  • .coveragerc
  • LICENSE
  • CONTRIBUTING.md
  • .flake8
  • .gitattributes
  • setup.py
  • tutorials
    • classification
      • esim.ipynb
      • bert.ipynb
      • init.ipynb
    • ranking
      • duet.ipynb
      • esim.ipynb
      • knrm.ipynb
      • matchlstm.ipynb
      • match_srnn.ipynb
      • bert.ipynb
      • conv_knrm.ipynb
      • arci.ipynb
      • match_pyramid.ipynb
      • drmmtks.ipynb
      • anmm.ipynb
      • drmm.ipynb
      • init.ipynb
      • arcii.ipynb
      • dssm.ipynb
      • cdssm.ipynb
  • artworks
  • .travis.yml
  • README.md
  • tests
    • test_utils.py
    • trainer
      • test_trainer.py
    • test_embedding.py
    • models
      • test_models.py
      • test_base_model.py
    • dataloader
      • test_callbacks.py
      • test_dataset.py
    • data_pack
      • test_datapack.py
    • engine
      • test_param_table.py
      • test_base_preprocessor.py
      • test_base_task.py
      • test_hyper_spaces.py
    • tasks
      • test_tasks.py
    • __init__.py
    • test_metrics.py
    • test_datasets.py
    • test_losses.py
    • modules
      • test_modules.py
  • pytest.ini
  • requirements.txt
  • CODEOWNERS
  • .codecov.yml
  • .gitignore
  • docs
    • DOCCHECK.md
    • Makefile
    • source
      • model_reference.rst
      • modules.rst
      • index.rst
      • conf.py
    • make.bat
    • Readme.md
    • requirements.txt
  • MANIFEST.in

import nltk

from .unit import Unit


class Lemmatization(Unit):
    """Process unit for token lemmatization."""

    def transform(self, input_: list) -> list:
        """
        Lemmatization a sequence of tokens.

        :param input_: list of tokens to be lemmatized.

        :return tokens: list of lemmatizd tokens.
        """
        lemmatizer = nltk.WordNetLemmatizer()
        return [lemmatizer.lemmatize(token, pos='v') for token in input_]