hankcs--hanlp/docs/api/hanlp/datasets/tok/resources.md

resources

sighan2005

The Second International Chinese Word Segmentation Bakeoff took place over the summer of 2005.

pku

.. automodule:: hanlp.datasets.tokenization.sighan2005.pku
    :members:

msr

.. automodule:: hanlp.datasets.tokenization.sighan2005.msr
    :members:

as

.. automodule:: hanlp.datasets.tokenization.sighan2005.as_
    :members:

cityu

.. automodule:: hanlp.datasets.tokenization.sighan2005.cityu
    :members:

CTB6

.. automodule:: hanlp.datasets.tokenization.ctb6
    :members:

CTB8

.. automodule:: hanlp.datasets.parsing.ctb8

.. autodata:: CTB8_CWS_TRAIN
.. autodata:: CTB8_CWS_DEV
.. autodata:: CTB8_CWS_TEST

CTB9

.. automodule:: hanlp.datasets.parsing.ctb9

.. autodata:: CTB9_CWS_TRAIN
.. autodata:: CTB9_CWS_DEV
.. autodata:: CTB9_CWS_TEST