The ``BertCrfTagger`` encodes a sequence of text with a ``Seq2SeqEncoder``, then uses a Conditional Random Field model to predict a tag for e

Implements a basic text classifier: 1) Embed tokens using `text_field_embedder` 2) Get the CLS token 3) Final feedforward layer

Text classification data reader The data is assumed to be in jsonlines format each line is a json-dict with the following keys: 'text',

A dummy seq2seq encoder that just returns its inputs as is. Parameters ---------- input_dim : ``int``, required. The inp

Exactly like the CrfTagger in AllenNLP: https://github.com/allenai/allennlp/blob/master/allennlp/models/crf_tagger.py But differences in

Implements a basic text classifier: 1) Embed tokens using `text_field_embedder` 2) Seq2SeqEncoder, e.g. BiLSTM 3) Append the first an