The low priority dictionary which perform longest-prefix-matching on model predictions and combing them. Examples: >>> tok.dict_

r""" The high priority dictionary which perform longest-prefix-matching on inputs to split them into two subsets: 1. spans containing no keyw

r""" A custom dictionary to override predicted tags by performing longest-prefix-matching. Examples: >>> pos.dict_tags = {'HanLP'

r""" First-order Eisner algorithm for projective decoding. References: - Ryan McDonald, Koby Crammer and Fernando Pereira. 2005.

Evaluate using official CoNLL-X evaluation script (Yuval Krymolowski) Args: gold_file(str): The gold conllx file pred_file(str): The

Evaluation for unlabeled retrieval. Args: gold_spans: Set of tuples of (start, end). span_starts: span_ends: span_score

Single document summarization is the task of selecting a subset of the sentences which best represents a summary of the document, with a balance of sa