Source code for nlp_architect.data.conll

# ******************************************************************************
# Copyright 2017-2018 Intel Corporation
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ******************************************************************************
import re


# This file contains adapted open sourced code, publicly available at:
# https://github.com/elikip/bist-parser/blob/master/bmstparser/src/utils.py

# Things that were changed from the original:
# 1) Added input validation
# 2) Updated function and object names to dyNet 2.0.2 and Python 3
# 3) Removed external embeddings option
# 4) Reformatted code and variable names to conform with PEP8
# 5) Added dict_to_obj()
# 6) Added option for train() to get ConllEntry input
# 7) Added legal header

NUMBER_REGEX = re.compile("[0-9]+|[0-9]+\\.[0-9]+|[0-9]+[0-9,]+")


[docs]class ConllEntry: def __init__(self, eid, form, lemma, pos, cpos, feats=None, parent_id=None, relation=None, deps=None, misc=None): self.id = eid self.form = form self.norm = normalize(form) self.cpos = cpos.upper() self.pos = pos.upper() self.parent_id = parent_id self.relation = relation self.lemma = lemma self.feats = feats self.deps = deps self.misc = misc self.pred_parent_id = None self.pred_relation = None self.vec = None self.lstms = None def __str__(self): values = [str(self.id), self.form, self.lemma, self.cpos, self.pos, self.feats, str(self.pred_parent_id) if self.pred_parent_id is not None else None, self.pred_relation, self.deps, self.misc] return '\t'.join(['_' if v is None else v for v in values])
[docs]def normalize(word): return 'NUM' if NUMBER_REGEX.match(word) else word.lower()