nlp_architect.models.bist package

Submodules

nlp_architect.models.bist.decoder module

nlp_architect.models.bist.decoder.parse_proj(scores, gold=None)[source]

Parse using Eisner’s algorithm.

nlp_architect.models.bist.mstlstm module

class nlp_architect.models.bist.mstlstm.MSTParserLSTM(vocab, w2i, pos, rels, options)[source]

Bases: object

Underlying LSTM model for MSTParser used by BIST parser.

load(filename)[source]
predict(conll_path=None, conll=None)[source]
save(filename)[source]
train(conll_path)[source]

nlp_architect.models.bist.utils module

nlp_architect.models.bist.utils.get_options_dict(activation, lstm_dims, lstm_layers, pos_dims)[source]

Generates dictionary with all parser options.

nlp_architect.models.bist.utils.is_conllu(path)[source]

Determines if the file is in CoNLL-U format.

nlp_architect.models.bist.utils.read_conll(path)[source]

Yields CoNLL sentences read from CoNLL formatted file..

nlp_architect.models.bist.utils.run_eval(gold, test)[source]

Evaluates a set of predictions using the appropriate script.

nlp_architect.models.bist.utils.vocab(conll_path)[source]
nlp_architect.models.bist.utils.write_conll(path, conll_gen)[source]

Writes CoNLL sentences to CoNLL formatted file.

Module contents