A single training/test example for simple sequence classification.

Embedding layer that initialises its values to using a truncated normal variable scaled by the inverse of the embedding dimension.

Class that manages dynamic loss scaling. It is recommended to use :class:`DynamicLossScaler` indirectly, by supplying ``dynamic_loss_scale=T

This DatasetReader is designed to read in the English OntoNotes v5.0 data in the format used by the CoNLL 2011/2012 shared tasks. In order to

Reused tree object from stanfordnlp/treelstm.

This DatasetReader is designed to read in the CoNLL-2005 SRL data. The file path provided to this class can then be any of the train, test or

A class representing the annotations available for a single CONLL formatted sentence. Parameters ---------- domain_placeholder : ``st

NOTE: This class has been copied verbatim from the separate Dense and Sparse versions of Adam in Pytorch. Implements Adam algorithm with

Class that manages a static loss scale. This class is intended to interact with :class:`FP16_Optimizer`, and should not be directly manipula

A class representing the annotations available for a single CONLL formatted sentence. Parameters ---------- document_id : ``str``

Same as BertEmbeddings with a tiny tweak for positional embeddings indexing.

Utility module that implements:: def forward(self, input): return input.half()

Construct the embeddings from word, position and token_type embeddings.

An abstract class to handle weights initialization and a simple interface for dowloading and loading pretrained models.

This DatasetReader is designed to read in the English OntoNotes v5.0 data for semantic role labelling. It returns a dataset of instances with

Base class for data converters for sequence classification data sets.

Convert model to half precision in a batchnorm-safe way.

:class:`FP16_Optimizer` is designed to wrap an existing PyTorch optimizer, and manage static or dynamic loss scaling and master weights in a

Linear warmup and then linear decay. Linearly increases learning rate from 0 to 1 over `warmup_steps` training steps. Linearly decrea

A wrapper classifier for GNNRelationModel.

We make use of the GRUCell in Pytorch. This formulation is somewhat different from the paper: "https://arxiv.org/pdf/1910.06764.pdf" Stab

A single set of features of data.

With label smoothing, KL-divergence between q_{smoothed ground truth prob.}(w) and p_{prob. computed by model}(w) is minimized.

Processor for OntoNotes-5.0 NER task

This DatasetReader is designed to read in the English OntoNotes v5.0 data for fine-grained named entity recognition. It returns a dataset of

This class uses the external srl-eval.pl script for computing the CoNLL SRL metrics. Note that this metric reads and writes from disk quite a

This DatasetReader is designed to read in the English OntoNotes v5.0 data for semantic role labelling. It returns a dataset of instances with

Processor for the SST-2 data set (GLUE version).

Processor for the TACRED relation extraction data set (EMNLP 2017)