def process_sentence(sentence_id, annotations, lines): merged = merge_tokens(sentence_id, annotations, lines) normalized = normalize_numerical_fes(sentence_id, merged) # insert correct token ids for i, p in enumerate(normalized): p[1] = str(i) clean = OrderedSet() for line in normalized: clean.add('\t'.join(line)) return clean
def process_sentence(sentence_id, annotations, lines): """ process a single sentence by mergind the tokens and normalizing numerical expressions """ merged = merge_tokens(sentence_id, annotations, lines) normalized = normalize_numerical_fes(sentence_id, merged) # insert correct token ids for i, p in enumerate(normalized): p[1] = str(i) clean = OrderedSet() for line in normalized: clean.add('\t'.join(line)) return clean
def process_sentence(sentence_id, annotations, lines): """ process a single sentence by merging the tokens and normalizing numerical expressions :param str sentence_id: The ID of this sentence :param dict annotations: The data about this sentence's FEs :param list lines: The POS tagging of this sentence :return: The processed sentence :rtype: list """ merged = merge_tokens(sentence_id, annotations, lines) normalized = normalize_numerical_fes(sentence_id, merged) # insert correct token ids for i, p in enumerate(normalized): p[1] = str(i) clean = OrderedSet() for line in normalized: clean.add('\t'.join(line)) return clean