Natural Language Processing (NLP)

Text processing, sentiment analysis, and natural language understanding libraries. Packages among the 3,000 most downloaded in the past 90 days.

21 packages
  • inflex 2.1.0

    An Elixir library for handling word inflections.

    384
    384.5k last 90 days
  • tokenizers 0.5.1

    Bindings to Hugging Face Tokenizers for Elixir

    101
    63.5k last 90 days
  • address_us 0.4.3

    Library for parsing US Addresses into their individual parts.

    31
    21.8k last 90 days
  • text_chunker 0.6.1

    An Elixir library for semantic text chunking.

    110
    19.7k last 90 days
  • stemmer 1.2.0

    An English (Porter2) stemming implementation in Elixir.

    154
    14.7k last 90 days
  • fast_ngram 1.3.0

    A fast and unicode aware letter & word N-gram library written in Elixir.

    3
    12.5k last 90 days
  • expletive 0.1.6

    Profanity detection and sanitization library

    48
    9.7k last 90 days
  • inflex28 2.1.0

    An Elixir library for handling word inflections.

    0
    9.1k last 90 days
  • afinn 0.3.0

    Sentiment analysis in Elixir. Languages supported: English, Danish

    3
    7.3k last 90 days
  • tiktoken 0.4.2

    Elixir bindings for Tiktoken tokenizer

    25
    6.5k last 90 days
  • avs_an 3.0.1

    Find the english language indeterminate article ("a" or "an") for a word.

    55
    5.8k last 90 days
  • alchemic_pinyin 0.1.2

    中文汉字转拼音.

    18
    5.2k last 90 days
  • corenlp 0.1.2

    This package provides a client interface to a Stanford CoreNLP Server for natural language processing (NLP) of textual content.

    15
    4.3k last 90 days
  • verbs 0.6.1

    Conjugates English verbs

    5
    4.3k last 90 days
  • paasaa 1.0.0

    Natural language detection

    143
    4.2k last 90 days
  • tesseract_ocr 0.1.5

    Elixir wrapper for Tesseract OCR, an open source text recognition engine.

    60
    3.8k last 90 days
  • google_api_language 0.16.3

    Cloud Natural Language API client library. Provides natural language understanding technologies, such as sentiment analysis, entity recognition, entity sentiment analysis, and other text annotations, to developers.

    1.1k
    3.7k last 90 days
  • aho_corasick_nif

    Aho-Corasick string matching algorithm implemented as a NIF wrapper of the Rust crate aho-corasick

    1
    3.5k last 90 days
  • gpt3_tokenizer 0.1.1

    OpenAI GPT-3 Tokenizer

    30
    3.4k last 90 days
  • text 0.6.2

    Text analysis and processing for Elixir including ngram, language detection and more.

    77
    3.3k last 90 days
  • lingua 0.3.6

    An Elixir wrapper around the Rust Lingua language detection library.

    16
    3.3k last 90 days