Print the dependency tree horizontally Args: arrows: _do_print_debug_info: (Default value = False) Returns:

Print a labeled sentence into CoNLL format. Args: fout: tokens: labels: Returns:

code for loading AMR from a set of files - use_recategorization: use graph recategorization trick - dereify: Dereify edges in g that

Read in additional chunks until it is yieldable.

Compute the recall. The recall is the ratio ``tp / (tp + fn)`` where ``tp`` is the number of true positives and ``fn`` the number of fals

Edge labels such as ARGx, ARGx-of, and 'opx' should only appear at most once in each node's outgoing edges.

Initialize the transition parameters. The parameters will be initialized randomly from a uniform distribution between -0.1 and 0.1.

Args: Returns: Precondition: self.yieldable() must be True

Save model weights to a directory. Args: save_dir: The directory to save weights into. filename: A file name for weig

An iterator over the sentences in an individual CONLL formatted file.

Computes the cross entropy loss of a sequence, weighted with respect to some user provided weights. Note that the weighting here is not the same a

Restrict TensorFlow to only use the GPU of idx Args: idx: (Default value = 0) Returns:

Copied from https://github.com/huggingface/transformers/blob/7b75aa9fa55bee577e2c7403301ed31103125a35/src/transformers/trainer.py#L76 Args:

Determines whether data is a filepath. Args: data: Data to check. Returns: ``True`` to indicate it's a filepath.

Compute correlation between 2 1-D vectors. Adopted from https://discuss.pytorch.org/t/spearmans-correlation/91931/5 Args: x: Shape (N

A handy method to perform longest-prefix-matching on a batch of sentences. It tokenize each sentence, record the chunks being either a key in

Checks if a chunk started between the previous and current word. Args: prev_tag: previous chunk tag. tag: current chunk tag. pr

Args: v: index: stack: Returns:

Args: v: index: stack: Returns:

Args: v: index: stack: Returns:

https://stackoverflow.com/a/53668338/3730690 Args: model: tf.keras.Model: Returns:

Adopted from Timothy Dozat https://github.com/tdozat/Parser/blob/master/lib/models/nn.py Args: parse_probs(NDArray): seq_len x seq_len, the

Text classification is the task of assigning a sentence or document an appropriate category. The categories depend on the chosen data

Given a tag sequence encoded with IOB1 labels, recode to BIOUL. In the IOB1 scheme, I is a token inside a span, O is a token outside a s

Convert to :class:`~hanlp_common.conll.CoNLLSentence`. Args: tok (str): Field name for tok. lem (str): Field