OSCAR word freq icu v1.0

OSCAR word freq v0.1 buit from icu word tokenize

Authors: Korakot Chaovavanich @korakot

from https://web.facebook.com/groups/colab.thailand/permalink/1524070061101680/?_rdc=1&_rdr

TNC unigarm 201712 and bi/ti-garm 201705

• 201705_2gram.txt:
• 201705_3gram.txt:
• tncwordfreq-201712.xlsx:

It is mrror TNC word frequency from Thai National Corpus (TNC)

Web: http://www.arts.chula.ac.th/ling/tnc/searchtnc/

LST20 CLS v0.2

• change features name

LST20 v0.2.3

-pos_lst20_perceptron-v0.2.3.pkl:

• pos_lst20_unigram-v0.2.3.json:

LST20 Part-of-speech

• port LST20 model

LST20 CLS v0.1

lst20-cls-v0.1

Update db.json

LST20 v0.2.2

• Rename taggers to pos_lst20_unigram and pos_lst20_perceptron, following the convention of other POS taggers in PyThaiNLP
• Minify Unigram JSON file

LST20 v0.2

lst20-v0.2

Update db.json

LST20 v0.1

lst20-v0.1

Update LICENSE

wiki_lm_lstm v0.32

• authors : Charin Polpanumas
• description : ULMFit for LSTM
• license : cc-by-sa-4.0
• url : https://github.com/cstorm125/thai2fit/

thai2fit_wv v0.1

thai2fit_wv v0.1

• Authors : Charin Polpanumas
• Description : thai2vec word embeddings
• License : cc-by-sa-4.0
• Url : https://github.com/cstorm125/thai2fit/