# -*- coding: utf-8 -*-
# Copyright (C) 2016-2023 PyThaiNLP Project
# 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
# 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.
from typing import List, Tuple
sent: List[Tuple[str, str]], engine: str = "crf", corpus: str = "orchidpp"
) -> List[str]:
This function parses Thai sentence to phrase structure in IOB format.
:param list sent: list [(word, part-of-speech)]
:param str engine: chunk parse engine (now, it has crf only)
:param str corpus: chunk parse corpus (now, it has orchidpp only)
:return: a list of tuples (word, part-of-speech, chunking)
from pythainlp.tag import chunk_parse, pos_tag
tokens = ["ผม", "รัก", "คุณ"]
tokens_pos = pos_tag(tokens, engine="perceptron", corpus="orchid")
# output: ['B-NP', 'B-VP', 'I-VP']
from .crfchunk import CRFchunk
_engine = CRFchunk()