Source code for ontolearn.nces_utils

# -----------------------------------------------------------------------------
# MIT License
#
# Copyright (c) 2024 Ontolearn Team
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
# -----------------------------------------------------------------------------

"""NCES utils."""
from tokenizers import Tokenizer
from tokenizers.models import BPE
from tokenizers.trainers import BpeTrainer
from tokenizers.pre_tokenizers import WhitespaceSplit
from transformers import PreTrainedTokenizerFast
import os
import random

os.environ["TOKENIZERS_PARALLELISM"] = "false"


[docs] class SimpleSolution: def __init__(self, vocab, atomic_concept_names): self.name = 'SimpleSolution' self.atomic_concept_names = atomic_concept_names tokenizer = Tokenizer(BPE(unk_token='[UNK]')) trainer = BpeTrainer(special_tokens=["[UNK]", "[CLS]", "[SEP]", "[PAD]", "[MASK]"],show_progress=False) tokenizer.pre_tokenizer = WhitespaceSplit() tokenizer.train_from_iterator(vocab, trainer) self.tokenizer = PreTrainedTokenizerFast(tokenizer_object=tokenizer) self.tokenizer.pad_token = "[PAD]"
[docs] def predict(self, expression: str): atomic_classes = [atm for atm in self.tokenizer.tokenize(expression) if atm in self.atomic_concept_names] if atomic_classes == []: # If no atomic class found, then randomly pick and use the first 3 random.shuffle(self.atomic_concept_names) atomic_classes = self.atomic_concept_names[:3] return " ⊔ ".join(atomic_classes)