Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.

Applies the lemma rule to the form to generate the lemma Args: form: lemma_rule: Returns:

Build dataloader for training, dev and test sets. It's suggested to build vocabs in this method if they are not built yet. Args:

Loads a data file into a list of `InputBatch`s `cls_token_at_end` define the location of the CLS token: - False (Default, BERT/XLM

Coreference resolution is the task of clustering mentions in text that refer to the same underlying real world entities. @param text A piece of text,

r""" Factorizes the tree into a sequence. The tree is traversed in pre-order. Args: tree (tree.Tree): The tree to be

Transform file to inputs. The inputs are defined as raw features (e.g. words) to be processed into more features (e.g. forms and char

# Returns The accumulated accuracy.

Get the token using its index. Args: idx: The index to a token. Returns:

Longest-prefix-matching which tries to match the longest keyword sequentially from the head of the text till its tail. By definition, the matc

Prune (to discard) samples according to a criterion. Args: criterion: A functions takes a sample as input and output ``True`` if

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

Shift input ids one token to the right.

Redirect stdout to else where. Copied from https://stackoverflow.com/questions/4675728/redirect-stdout-to-a-file-in-python/22434262#22434262

Text style transfer aims to change the style of the input text to the target style while preserving its content. Args: t

Convert to json string. Args: ensure_ascii: ``False`` to allow for non-ascii text. indent: Indent per nested structur

Update the vocab with these tokens by adding them to vocab one by one. Args: tokens: Iterable[str]: Returns:

Convert predicted tensors to outputs Parameters ---------- X : Union[tf.Tensor, Tuple[tf.Tensor]] The in