Classical Language Toolkit

[First posted in AWOL 17 May 2014, updated 26 June 2016]

Classical Language Toolkit

The Classical Language Toolkit (CLTK) offers natural language processing support for Classical languages. In some areas, it extends the NLTK. The goals of the Classical Language Toolkit (CLTK) are to:

• compile analysis-friendly corpora in a variety of Classical languages (currently available for Chinese, Coptic, Greek, Latin, Pali, and Tibetan);
• gather, improve, and generate linguistic data required for NLP (Greek and Latin are in progress, with more in the pipeline);
• develop a free and open platform for generating reproducible, scientific research that advances the study of the languages and literatures of the ancient world.

The project's source is hosted on GitHub and the homepage is http://cltk.org.

Contents

• About
• Citation
• Installation
  • With Pip
  • From source
• Importing Corpora
  • Listing corpora
  • Importing a corpus
• Chinese
  • Corpora
• Coptic
  • Corpora
• Greek
  • Converting Beta Code to Unicode
  • Converting TLG texts with TLGU
  • Information Retrieval
  • Lemmatization
  • Named Entity Recognition
  • POS tagging
  • Prosody Scanning
  • Sentence Tokenization
  • Stopword Filtering
  • Text Cleanup
  • TLG Indices
  • Word2Vec
• Latin
  • Clausulae Analysis
  • Converting J to I, V to U
  • Converting PHI texts with TLGU
  • Information Retrieval
  • Lemmatization
  • Making POS training sets
  • Named Entity Recognition
  • PHI Indices
  • POS tagging
  • Prosody Scanning
  • Sentence Tokenization
  • Stemming
  • Stopword Filtering
  • Syllabifier
  • Text Cleanup
  • Word Tokenization
  • Word2Vec
• Multilingual
  • Concordance
  • Corpora
  • Information Retrieval (regex, keyword expansion)
  • Information Retrieval (boolean)
  • N–grams
  • Text Reuse
  • Word count
  • Word frequency lists
  • Word tokenization
• Pali
  • Corpora
• Sanskrit
  • Corpora
  • Transliterator
• Telugu
  • Corpora
• Tibetan
  • Corpora