Tokenize a string. Modified in order to handle sentences with recategorization pointers

Get the information about server and your client. Returns: A dict containing your rate limit and server version etc.

Abstractive Summarization is the task of generating a short and concise summary that captures the salient ideas of the source text. The generated summ

r""" Abstractive Summarization is the task of generating a short and concise summary that captures the salient ideas of the source text. The g

Accuracy classification score. In multilabel classification, this function computes subset accuracy: the set of labels predicted for a sa

Args: sample: pos_key: bos: A special token inserted to the head of tokens. Returns:

* Calculates the cross-entropy loss between `attention_S` and `attention_T`, where softmax is to applied on ``dim=-1``. * If the `inputs_mas

* Calculates the cross-entropy loss between `attention_S` and `attention_T`, where softmax is to applied on ``dim=-1``. * If the shape is (*b

* Calculates the mse loss between `attention_S` and `attention_T`. * If the `inputs_mask` is given, masks the positions where ``input_mask==0

* Calculates the mse loss between `attention_S` and `attention_T`. * If the the shape is (*batch_size*, *num_heads*, *length*, *length*), su

Convert batched inputs to batches of samples Args: corpus(list): A list of inputs indices(list): A list of indices, each

Given a sequence corresponding to BIOUL tags, extracts spans. Spans are inclusive and can be of zero length, representing a single word span.

Given a sequence corresponding to BMES tags, extracts spans. Spans are inclusive and can be of zero length, representing a single word span.

Build `Layer` Args: input_shape: Returns:

Build a dataloader for training or evaluation. Args: data: Either a path or a list of samples. transform: Th