├── .gitignore ├── README.md ├── kaznlp ├── __init__.py ├── docs │ └── morphology-tagset.MD ├── lid │ ├── __init__.py │ ├── char.mdl │ ├── lidnb.py │ └── word.mdl ├── models │ ├── __init__.py │ └── hmm.py ├── morphology │ ├── __init__.py │ ├── analyzers.py │ ├── mdl │ │ ├── ligs.1gram │ │ ├── ligs.2gram │ │ ├── ligs.3gram │ │ ├── lkps │ │ ├── md │ │ ├── prms.1gram │ │ ├── prms.2gram │ │ ├── prms.3gram │ │ ├── sfx │ │ ├── stm_lig │ │ ├── tm │ │ └── wrd_tag │ ├── taggers.py │ └── utils.py ├── normalization │ ├── __init__.py │ ├── emojiresolver.py │ └── ininorm.py └── tokenization │ ├── __init__.py │ ├── tokhmm.mdl │ ├── tokhmm.py │ └── tokrex.py └── tutorial.py /.gitignore: -------------------------------------------------------------------------------- 1 | *.py[cod] 2 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/README.md -------------------------------------------------------------------------------- /kaznlp/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /kaznlp/docs/morphology-tagset.MD: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/docs/morphology-tagset.MD -------------------------------------------------------------------------------- /kaznlp/lid/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /kaznlp/lid/char.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/lid/char.mdl -------------------------------------------------------------------------------- /kaznlp/lid/lidnb.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/lid/lidnb.py -------------------------------------------------------------------------------- /kaznlp/lid/word.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/lid/word.mdl -------------------------------------------------------------------------------- /kaznlp/models/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /kaznlp/models/hmm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/models/hmm.py -------------------------------------------------------------------------------- /kaznlp/morphology/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /kaznlp/morphology/analyzers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/morphology/analyzers.py -------------------------------------------------------------------------------- /kaznlp/morphology/mdl/ligs.1gram: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/morphology/mdl/ligs.1gram -------------------------------------------------------------------------------- /kaznlp/morphology/mdl/ligs.2gram: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/morphology/mdl/ligs.2gram -------------------------------------------------------------------------------- /kaznlp/morphology/mdl/ligs.3gram: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/morphology/mdl/ligs.3gram -------------------------------------------------------------------------------- /kaznlp/morphology/mdl/lkps: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/morphology/mdl/lkps -------------------------------------------------------------------------------- /kaznlp/morphology/mdl/md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/morphology/mdl/md -------------------------------------------------------------------------------- /kaznlp/morphology/mdl/prms.1gram: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/morphology/mdl/prms.1gram -------------------------------------------------------------------------------- /kaznlp/morphology/mdl/prms.2gram: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/morphology/mdl/prms.2gram -------------------------------------------------------------------------------- /kaznlp/morphology/mdl/prms.3gram: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/morphology/mdl/prms.3gram -------------------------------------------------------------------------------- /kaznlp/morphology/mdl/sfx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/morphology/mdl/sfx -------------------------------------------------------------------------------- /kaznlp/morphology/mdl/stm_lig: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/morphology/mdl/stm_lig -------------------------------------------------------------------------------- /kaznlp/morphology/mdl/tm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/morphology/mdl/tm -------------------------------------------------------------------------------- /kaznlp/morphology/mdl/wrd_tag: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/morphology/mdl/wrd_tag -------------------------------------------------------------------------------- /kaznlp/morphology/taggers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/morphology/taggers.py -------------------------------------------------------------------------------- /kaznlp/morphology/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/morphology/utils.py -------------------------------------------------------------------------------- /kaznlp/normalization/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /kaznlp/normalization/emojiresolver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/normalization/emojiresolver.py -------------------------------------------------------------------------------- /kaznlp/normalization/ininorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/normalization/ininorm.py -------------------------------------------------------------------------------- /kaznlp/tokenization/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /kaznlp/tokenization/tokhmm.mdl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/tokenization/tokhmm.mdl -------------------------------------------------------------------------------- /kaznlp/tokenization/tokhmm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/tokenization/tokhmm.py -------------------------------------------------------------------------------- /kaznlp/tokenization/tokrex.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/kaznlp/tokenization/tokrex.py -------------------------------------------------------------------------------- /tutorial.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nlacslab/kaznlp/HEAD/tutorial.py --------------------------------------------------------------------------------