This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import re, string, sys, nltk | |
| from nltk.stem.wordnet import WordNetLemmatizer | |
| from nltk.corpus import wordnet | |
| from joblib import Parallel, delayed | |
| lmtzr = WordNetLemmatizer() | |
| pattern=re.compile(r'[^a-zA-Z ]') | |
| def get_wordnet_pos(treebank_tag): | |
| if treebank_tag.startswith('J'): |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import re, string, sys, nltk, timeit | |
| from nltk.stem.wordnet import WordNetLemmatizer | |
| from nltk.corpus import wordnet | |
| from joblib import Parallel, delayed | |
| lmtzr = WordNetLemmatizer() | |
| pattern=re.compile(r'[^a-zA-Z ]') | |
| tag_to_type = {'J': wordnet.ADJ, 'V': wordnet.VERB, 'R': wordnet.ADV} | |
| def get_wordnet_pos(treebank_tag): |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import re, string, sys, nltk, timeit | |
| from nltk.stem.wordnet import WordNetLemmatizer | |
| from nltk.corpus import wordnet | |
| from joblib import Parallel, delayed | |
| lmtzr = WordNetLemmatizer() | |
| pattern=re.compile(r'[^a-zA-Z ]') | |
| tag_to_type = {'J': wordnet.ADJ, 'V': wordnet.VERB, 'R': wordnet.ADV} | |
| def get_wordnet_pos(treebank_tag): |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import re, string, sys, nltk, timeit | |
| from nltk.stem.wordnet import WordNetLemmatizer | |
| from nltk.corpus import wordnet | |
| from joblib import Parallel, delayed | |
| lmtzr = WordNetLemmatizer() | |
| pattern=re.compile(r'[^a-zA-Z ]') | |
| tag_to_type = {'J': wordnet.ADJ, 'V': wordnet.VERB, 'R': wordnet.ADV} | |
| def get_wordnet_pos(treebank_tag): |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import re, string, sys, nltk, timeit | |
| from nltk.stem.wordnet import WordNetLemmatizer | |
| from nltk.corpus import wordnet | |
| from joblib import Parallel, delayed | |
| lmtzr = WordNetLemmatizer() | |
| pattern=re.compile(r'[^a-zA-Z ]') | |
| tag_to_type = {'J': wordnet.ADJ, 'V': wordnet.VERB, 'R': wordnet.ADV} | |
| def get_wordnet_pos(treebank_tag): |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import re, string, sys, nltk, timeit | |
| from nltk.stem.wordnet import WordNetLemmatizer | |
| from nltk.corpus import wordnet | |
| from joblib import Parallel, delayed | |
| lmtzr = WordNetLemmatizer() | |
| pattern=re.compile(r'[^a-zA-Z ]') | |
| shortword = re.compile(r'\W*\b\w{1,2}\b') | |
| tag_to_type = {'J': wordnet.ADJ, 'V': wordnet.VERB, 'R': wordnet.ADV} |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import re, string, sys, nltk, timeit | |
| from nltk.stem.wordnet import WordNetLemmatizer | |
| from nltk.corpus import wordnet | |
| from joblib import Parallel, delayed | |
| lmtzr = WordNetLemmatizer() | |
| pattern=re.compile(r'[^a-zA-Z ]') | |
| shortword = re.compile(r'\W*\b\w{1,2}\b') | |
| tag_to_type = {'J': wordnet.ADJ, 'V': wordnet.VERB, 'R': wordnet.ADV} |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import nltk, timeit | |
| from nltk.stem.wordnet import WordNetLemmatizer | |
| from nltk.corpus import wordnet | |
| from joblib import Parallel, delayed | |
| from functools32 import lru_cache | |
| lmtzr = WordNetLemmatizer() | |
| lemmatize = lru_cache(maxsize=100000)(lmtzr.lemmatize) | |
| tag_to_type = {'J': wordnet.ADJ, 'V': wordnet.VERB, 'R': wordnet.ADV} |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import nltk, timeit | |
| from nltk.stem.wordnet import WordNetLemmatizer | |
| from nltk.corpus import wordnet | |
| from joblib import Parallel, delayed | |
| lmtzr = WordNetLemmatizer() | |
| tag_to_type = {'J': wordnet.ADJ, 'V': wordnet.VERB, 'R': wordnet.ADV} | |
| def get_wordnet_pos(treebank_tag): | |
| return tag_to_type.get(treebank_tag[:1], wordnet.NOUN) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import nltk, timeit | |
| from nltk.stem.wordnet import WordNetLemmatizer | |
| from nltk.corpus import wordnet | |
| from joblib import Parallel, delayed | |
| lmtzr = WordNetLemmatizer() | |
| tag_to_type = {'J': wordnet.ADJ, 'V': wordnet.VERB, 'R': wordnet.ADV} | |
| def get_wordnet_pos(treebank_tag): | |
| return tag_to_type.get(treebank_tag[:1], wordnet.NOUN) |