It supports 3D arrays of tokens. Args: some_token: Tokens of 1D to 3D Returns: A list of indices.

Predict on data fed by user. This method calls :meth:`~hanlp.common.torch_component.predict` but decorates it with ``torch.no_grad``.

A shortcut for :func:`~hanlp.common.component.predict`. Args: *args: Any type of data subject to sub-classes **k

A shortcut of :meth:`~hanlp_restful.HanLPClient.parse`.

Delete a task (and every resource it owns) from this component. Args: task_name: The name of the task to be deleted. Exa

Closes all opened its file handler and propagates all exceptions on exit.

Get the index-th sample in this dataset. Args: index: Either a integer index of a list of indices. Returns: Either a sa

Get the index/indices associated with a token or a list of tokens or vice versa. Args: key: ``str`` for token(s) and ``int`` for

A transition based lemmatizer using transformer as encoder. Args: **kwargs: Predefined config.

r"""Transformer based implementation of "Effective Neural Solution for Multi-Criteria Word Segmentation" (:cite:`he2019effective`). It uses an

A tokenizer using transformer tagger for span prediction. It features with 2 high performance dictionaries to handle edge cases in real appli

An old-school tagger using non-contextualized embeddings and RNNs as context layer. Args: **kwargs: Predefined config.

A shallow tagging model use transformer as decoder. Args: encoder: A pretrained transformer. num_labels: Size

r"""A simple tagger using transformers and a linear layer with an optional CRF (:cite:`lafferty2001conditional`) layer for NER task. I

An old-school RNN tagger using word2vec or fasttext embeddings. Args: **kwargs: Predefined config.

An implementation of Named Entity Recognition as Dependency Parsing (:cite:`yu-etal-2020-named`). It treats every possible span as a candidate

An implementation of the biaffine decoder in "Named Entity Recognition as Dependency Parsing" (:cite:`yu-etal-2020-named`). Args:

Parameters ---------- prediction : numpy.ndarray a predicted dependency tree where prediction[dep_idx] = head_id

Two-stage CRF Parsing (:cite:`ijcai2020-560`). Args: **kwargs: Predefined config.

Universal Dependencies Parsing (lemmatization, features, PoS tagging and dependency parsing) implementation of "75 Languages, 1 Model: Parsing