Package `dhivehi_nlp`

A natural language processing library for the Dhivehi language.

Expand source code

"""
A natural language processing library for the Dhivehi language.
"""

Sub-modules

dhivehi_nlp.corpus: Collections of various Dhivehi texts …
dhivehi_nlp.dictionary: Get definitions definitions of Dhivehi words and the word list. Definitions obtained from radheef.mv …
dhivehi_nlp.language_models: Create language models to predict future additions. Language models will give probability based on selected ngram. An ngram is contiguous sequence of …
dhivehi_nlp.stemmer: Remove suffixes from words to return their root form …
dhivehi_nlp.stopwords: Remove stopwords from text and return the resulting tokens …
dhivehi_nlp.tagger: Tag words in text according to specified rules or patterns. For example, tagging words based on which part of speech it belongs to …
dhivehi_nlp.tokenizer: Tokenize text into separate sentences or words (tokens) …
dhivehi_nlp.trigram_similarity: Trigram similarity divides words or phrases into sequences of three consecutive letters, placed in a set where the order doesn't matter and duplicates …