podium.preproc.lemmatizer package¶

Submodules¶

podium.preproc.lemmatizer.croatian_lemmatizer module¶

Module Croatian Lemmatizer loads already prepared lemmatizer dictionaries. It can return all possible word inflections for a lemma, or return the lemma of any word inflexion for the Croatian language.

class podium.preproc.lemmatizer.croatian_lemmatizer.CroatianLemmatizer(**kwargs)¶

Bases: object

Class for lemmatizing words and fetching word inflections for a given lemma

BASE_FOLDER¶

folder to download lemmatizer resources

Type: str

MOLEX14_LEMMA2WORD¶

dictionary file path containing lemma to words mappings

Type: str

MOLEX14_WORD2LEMMA¶

dictionary file path containing word to lemma mappings

Type: str

get_words_for_lemma(lemma)¶

Returns a list of words that shares the provided lemma.

Parameters: word (str) – Word lemma to find words that share this lemma
Returns: List of words that share the lemma provided uppercased at same chars as lemma provided
Return type: list(str)
Raises: ValueError – If no words for the provided lemma are found.

podium.preproc.lemmatizer.croatian_lemmatizer.get_croatian_lemmatizer_hook(**kwargs)¶

Method obtains croatian lemmatizer hook.

Parameters: kwargs (dict) – Croatian lemmatizer arguments.

Module contents¶

Package contains modules for lemmatizing.

class podium.preproc.lemmatizer.CroatianLemmatizer(**kwargs)¶