The Classical Language Toolkit

Overview

Notice: This Git branch (dev) contains the CLTK's upcoming major release (v. 1.0.0). See https://github.com/cltk/cltk/tree/master and https://docs.cltk.org/ for the legacy code and docs.

travis rtd codecov pypi zenodo binder

The Classical Language Toolkit (CLTK) is a Python library offering natural language processing (NLP) for the languages of pre–modern Eurasia.

Installation

For the CLTK's latest pre-release version:

$ pip install --pre cltk
Requirements:

Documentation

Documentation at https://dev.cltk.org.

Citation

@Misc{johnsonetal2014,
 author = {Johnson, Kyle P. and Patrick Burns and John Stewart and Todd Cook},
 title = {CLTK: The Classical Language Toolkit},
 url = {https://github.com/cltk/cltk},
 year = {2014--2020},
}

License

Copyright (c) 2014-2021 Kyle P. Johnson under the MIT License.

Comments
  • Add Sanskrit stopwords

    Add Sanskrit stopwords

    For @Akhilesh28. (Please assign this to yourself.)

    In Sanskrit, a stopword list would include, at least: pronouns and determiners (source), and upasarga (verbal prefix / "preverb" / "preposition") and nipāta (particle) (which I read about here). Also add anything like conjunctions, particles, and interjections.

    Just putting together this list shouldn't take more than one week. Let us know if you're having problems. You can post your stopwords here, first, as a "gist": https://gist.github.com/

    opened by kylepjohnson 55
  • Add IPA Phonetic Transcription for Greek

    Add IPA Phonetic Transcription for Greek

    This ticket is for Jack Duff, with @jtauber generously assisting.

    The basic idea is to make a map of Greek letters and their IPA equivalents, something like:

    {'α': 'a',
    'αι', 'ai',
    'ζ': 'zd',
    'θ': 'tʰ'}
    

    Obviously, it won't all be so easy, due to proximal characters changing pronunciation (for example, "γ" being IPA "ɡ" but before ["κ", "χ", "γ", "μ"] becoming "ŋ").

    If you can get this down for Attic, then consider moving on to other dialects, like Ionic or Koine.

    Within the CLTK's architecture, the transliteration maps and logic should go into something like cltk/phonetics/greek/transcription.py. Or consider making a general transcription entry point at cltk/phonetics/transcription.py and then declaring a which language and dialect. I'll leave the implementation details to you two, though.

    enhancement 
    opened by kylepjohnson 51
  • Words to be added in Sanskrit's Stop Word Collection

    Words to be added in Sanskrit's Stop Word Collection

    • ~सः (He)~
    • ~स्वयम्(himself)~
    • तदीय(theres) -आसम्(be)
    • ज्ञा (have) -परि (with) -शक्नोति(can(verb)) -यद्(if) -कतम(which)

    add all the words in all their different cases, gender and and all 3 numbers(sin, dual, plural) . If you are doing it right, there must be 72 words exactly for each entity(including a few repetitions). Needs to be careful when it come to verb's word form, they are entirely different structures.

    File at: https://github.com/cltk/cltk/blob/master/cltk/stop/sanskrit/stops.py

    opened by nikheelpandey 42
  • Scraping srimad-bhagavadgita and valmiki ramayana.

    Scraping srimad-bhagavadgita and valmiki ramayana.

    • I am Scapping Sanskrit - English data from
      • Srimad-bhagavadgita : http://www.gitasupersite.iitk.ac.in/srimad
      • Valmiki Ramayana : http://www.valmiki.iitk.ac.in/

    Ping @kylepjohnson

    new corpus 
    opened by ghost 36
  • Add corpus for classical telugu

    Add corpus for classical telugu

    https://te.wikisource.org/wiki contains the classical telugu ithihasas, puranas, vedas, stothras, etc; So I would like to scrape them and add as a new corpus.

    Thank you.

    new corpus 
    opened by ghost 31
  • Make stopwords list for Old English

    Make stopwords list for Old English

    To generalize, I observe that there are different approaches to making stopword lists, based either on statistics (most common words, variously calculated) or grammar (definite and indefinite articles, pronouns, etc.) (or some combination).

    In doing this ticket, I would like you to do a little research on whether there exist any good lists for OE. If there is one, let's just take it. If not, we can do a little more research about what's right.

    enhancement easy 
    opened by kylepjohnson 29
  • Scraping Raw Classical Hindi Data

    Scraping Raw Classical Hindi Data

    I am scraping Raw Classical Hindi Data from http://ltrc.iiit.ac.in/showfile.php?filename=downloads/Classical_Hindi_Literature/SHUSHA/index.html @kylepjohnson

    new corpus 
    opened by Akirato 29
  • Add declining tool based on Collatinus and Eulexis ?

    Add declining tool based on Collatinus and Eulexis ?

    Hi there, It's been months I have been thinking about this and I do not think CLTK contains anything like that. Collatinus and Eulexis are two Lemmatizer and Decliners which are open source (their data is either open or easy to reconstruct. And they are a nice bunch of people).

    • Collatinus is in C
      • https://github.com/biblissima/collatinus is the most up to date source code for the flexer / lemmatizer
      • https://github.com/ycollatin/Collatinus-data is the repo for their data (but not up to date I guess ). It seems this is more up to date.
    • Eulexis is in php
      • https://github.com/biblissima/eulexis/blob/master/traitement.php For the whole code

    I'd be happy to convert the collatinus flexer for CLTK in the long run (give or take few months) but I think Eulexis and the lemmatizer part are out of my scope right now.

    What's your opinion on this ? This would help search APIs a lot for text which are not lemmatized.

    opened by PonteIneptique 28
  • Normalize Unicode throughout CLTK

    Normalize Unicode throughout CLTK

    I've been reading about normalize() and hope it will prevent normalization problems in the future. This builtin method solves the problem of accented characters made with combining diacritics not equaling precomposed characters. Examples of this appear in the testing library, where I have struggled to make two strings of accented Greek equal one another.

    Example of normalize() from Fluent Python by Luciano Ramalho (117-118):

    >>> from unicodedata import normalize
    >>> s1 = 'café' # composed "e" with acute accent
    >>> s2 = 'cafe\u0301' # decomposed "e" and acute accent 
    >>> len(s1), len(s2)
    (4, 5)
    >>> len(normalize('NFC', s1)), len(normalize('NFC', s2)) 
    (4, 4)
    >>> len(normalize('NFD', s1)), len(normalize('NFD', s2)) 
    (5, 5)
    >>> normalize('NFC', s1) == normalize('NFC', s2)
    True
    >>> normalize('NFD', s1) == normalize('NFD', s2) 
    True
    

    Solutions

    1. In core, use normalize with the argument 'NFC', as Fluent Python recommends. Not all Greek combining forms may reduce into precomposed … will need to be tested out.

    2. In tests, especially for assertEqual(), check that more complicated strings equal one another. Use normalize('NFC', <text>) on the comparison strings, too, if necessary.

    3. Use this to strip out accented characters coming from the PHI, which I don't do very gracefully here: https://github.com/kylepjohnson/cltk/blob/master/cltk/corpus/utils/formatter.py#L94

    Docs: https://docs.python.org/3.4/library/unicodedata.html#unicodedata.normalize

    enhancement 
    opened by kylepjohnson 25
  • add Latin WordNet API

    add Latin WordNet API

    The Latin WordNet API mimics the NLTK Princeton WordNet API in all major respects; however because the data is sourced from latinwordnet.exeter.ac.uk (rather than locally) a number of under-the-hood changes were made. Many access methods now return generators rather than lists, and in general the API is now 'lazy' where multiple HTTP requests would cause a bottleneck. The Resnick, Jiang-Conrath, and Lin similarity scoring functions work, but require availability of a corpus-based information content file (forthcoming).

    opened by wmshort 24
  • Write syllabifiers for Indian languages

    Write syllabifiers for Indian languages

    This ticket is for @soumyag213

    As discussed by email, you'll port this and related modules, to the CLTK, from the Indic NLP Library.

    For a first step, I'd like to see this working in your own repo, which you have started at: https://github.com/soumyag213/cltk-beginning-indo. In the README for this, I would like to see an example of its API. For example, I imagine you showing something like this is the Python shell (BTW I like iPython):

    In [1]: from indic_syllabifier import orthographic_syllabify
    In [2]: orthographic_syllabify('supercalifragilisticexpialidocious', 'tamil')
    Out[2]: 'su-per-cal-i-fra-gil-ist-ic-ex-pi-al-i-doc-ious'
    
    enhancement 
    opened by kylepjohnson 24
  • Processing text with square brackets using the Latin NLP pipeline

    Processing text with square brackets using the Latin NLP pipeline

    I noticed an anomaly processing Latin text with the default pipeline. The tokenizer fails to separate square brackets from the words they enclose.

    text = 'Benedictus XVI [Iosephus Aloisius Ratzinger] fuit papa et episcopus Romanus.'
    
    from cltk import NLP
    
    cltk_nlp = NLP('lat')
    cltk_nlp.analyze(text).tokens
    

    Result:

    ['Benedictus', 'XVI', '[Iosephus', 'Aloisius', 'Ratzinger]', 'fuit', 'papa', 'et', 'episcopus', 'Romanus', '.']
    

    The problem does not occur when the LatinWordTokenizer is used.

    from cltk.tokenizers.lat.lat import LatinWordTokenizer
    
    tokenizer = LatinWordTokenizer()
    tokenizer.tokenize(text)
    

    Result:

    ['Benedictus', 'XVI', '[', 'Iosephus', 'Aloisius', 'Ratzinger', ']', 'fuit', 'papa', 'et', 'episcopus', 'Romanus', '.']
    

    Environment: Windows 10 + python 3.9.13 + cltk 1.1.6.

    bug 
    opened by DavideMassidda 0
  • SpaCy process

    SpaCy process

    I added the spaCy process with a custom wrapper to translate Token from spacy to Word in cltk. The aim is to be able to use trained models provided by spaCy with CLTK.

    opened by clemsciences 0
  • A way to tell what tokens `LatinBackOffLemmatizer()` has failed to lemmatize

    A way to tell what tokens `LatinBackOffLemmatizer()` has failed to lemmatize

    In LatinBackOffLemmatizer() and the lemmatizers in its chain I can't seem to find an option to return an empty value (such as in OldEnglishDictionaryLemmatizer()'s best_guess=False option), instead of returning the input value, when the lemmatizer fails to assign a lemma.

    Without such an option, it doesn't seem possible to tell successful from unsuccessful lemmatization attempts programmatically, severely limiting the range of the lemmatizer's applications.

    question acknowledged feature-request 
    opened by langeslag 6
  • Bump certifi from 2022.5.18.1 to 2022.12.7

    Bump certifi from 2022.5.18.1 to 2022.12.7

    Bumps certifi from 2022.5.18.1 to 2022.12.7.

    Commits

    Dependabot compatibility score

    Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.


    Dependabot commands and options

    You can trigger Dependabot actions by commenting on this PR:

    • @dependabot rebase will rebase this PR
    • @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
    • @dependabot merge will merge this PR after your CI passes on it
    • @dependabot squash and merge will squash and merge this PR after your CI passes on it
    • @dependabot cancel merge will cancel a previously requested merge and block automerging
    • @dependabot reopen will reopen this PR if it is closed
    • @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
    • @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
    • @dependabot use these labels will set the current labels as the default for future PRs for this repo and language
    • @dependabot use these reviewers will set the current reviewers as the default for future PRs for this repo and language
    • @dependabot use these assignees will set the current assignees as the default for future PRs for this repo and language
    • @dependabot use this milestone will set the current milestone as the default for future PRs for this repo and language

    You can disable automated security fix PRs for this repo from the Security Alerts page.

    dependencies 
    opened by dependabot[bot] 0
  • Unicode issue with Greek accented vowels in prosody

    Unicode issue with Greek accented vowels in prosody

    Unicode has two code points for acute accented vowels, one in the Greek and Coptic block and one in the Greek extended block (for omicron they are U+03CC and U+1F79. The list of accented vowels only takes into account the acute accents in the Greek and Coptic block resulting in some vowels not being properly scanned.

    >>> from cltk.prosody.grc import Scansion
    >>> text_string = "πότνια, θῦμον"
    >>> Scansion()._make_syllables(text_string)
    [[['πότνι', 'α'], ['θῦ', 'μον']]]
    

    Expected behavior

    >>> from cltk.prosody.grc import Scansion
    >>> text_string = "πότνια, θῦμον"
    >>> Scansion()._make_syllables(text_string)
    [[['πο', 'τνι' , 'α'], ['θῦ', 'μον']]]
    

    Desktop

    • MacOS 13.0
    bug 
    opened by JoshuaCCampbell 1
  • Latin enclitic tokenizer broken?

    Latin enclitic tokenizer broken?

    Latin tokenizer does not separate -que, ne, ve. In line 147 of tokenizers/lat/lat.py I suggest: specific_tokens += [token[: -len(enclitic)]] + ["-"+enclitic] This fixed it for me.

    Mac OS 15.7 Python 3.9

    bug 
    opened by polycrates 3
Releases(1.0.15)
Owner
Classical Language Toolkit
Natural language processing for Classical languages
Classical Language Toolkit
xFormers is a modular and field agnostic library to flexibly generate transformer architectures by interoperable and optimized building blocks.

Description xFormers is a modular and field agnostic library to flexibly generate transformer architectures by interoperable and optimized building bl

Facebook Research 2.3k Jan 08, 2023
LegalNLP - Natural Language Processing Methods for the Brazilian Legal Language

LegalNLP - Natural Language Processing Methods for the Brazilian Legal Language ⚖️ The library of Natural Language Processing for Brazilian legal lang

Felipe Maia Polo 125 Dec 20, 2022
🛸 Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy

spacy-transformers: Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy This package provides spaCy components and architectures to use tr

Explosion 1.2k Jan 08, 2023
Skipgram Negative Sampling in PyTorch

PyTorch SGNS Word2Vec's SkipGramNegativeSampling in Python. Yet another but quite general negative sampling loss implemented in PyTorch. It can be use

Jamie J. Seol 287 Dec 14, 2022
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

ALBERT ***************New March 28, 2020 *************** Add a colab tutorial to run fine-tuning for GLUE datasets. ***************New January 7, 2020

Google Research 3k Dec 26, 2022
IMS-Toucan is a toolkit to train state-of-the-art Speech Synthesis models

IMS-Toucan is a toolkit to train state-of-the-art Speech Synthesis models. Everything is pure Python and PyTorch based to keep it as simple and beginner-friendly, yet powerful as possible.

Digital Phonetics at the University of Stuttgart 247 Jan 05, 2023
Pipeline for training LSA models using Scikit-Learn.

Latent Semantic Analysis Pipeline for training LSA models using Scikit-Learn. Usage Instead of writing custom code for latent semantic analysis, you j

Dani El-Ayyass 23 Sep 05, 2022
Ecommerce product title recognition package

revizor This package solves task of splitting product title string into components, like type, brand, model and article (or SKU or product code or you

Bureaucratic Labs 16 Mar 03, 2022
Simple program that translates the name of files into English

Simple program that translates the name of files into English. Useful for when editing/inspecting programs that were developed in a foreign language.

0 Dec 22, 2021
Natural Language Processing with transformers

we want to create a repo to illustrate usage of transformers in chinese

Datawhale 763 Dec 27, 2022
List of GSoC organisations with number of times they have been selected.

Welcome to GSoC Organisation Frequency And Details 👋 List of GSoC organisations with number of times they have been selected, techonologies, topics,

Shivam Kumar Jha 41 Oct 01, 2022
Behavioral Testing of Clinical NLP Models

Behavioral Testing of Clinical NLP Models This repository contains code for testing the behavior of clinical prediction models based on patient letter

Betty van Aken 2 Sep 20, 2022
A paper list of pre-trained language models (PLMs).

Large-scale pre-trained language models (PLMs) such as BERT and GPT have achieved great success and become a milestone in NLP.

RUCAIBox 124 Jan 02, 2023
Grading tools for Advanced NLP (11-711)Grading tools for Advanced NLP (11-711)

Grading tools for Advanced NLP (11-711) Installation You'll need docker and unzip to use this repo. For docker, visit the official guide to get starte

Hao Zhu 2 Sep 27, 2022
Converts text into a PDF of handwritten notes

Text To Handwritten Notes Converts text into a PDF of handwritten notes Explore the docs » · Report Bug · Request Feature · Steps: $ git clone https:/

UVSinghK 63 Oct 09, 2022
Bnagla hand written document digiiztion

Bnagla hand written document digiiztion This repo addresses the problem of digiizing hand written documents in Bangla. Documents have definite fields

Mushfiqur Rahman 1 Dec 10, 2021
simpleT5 is built on top of PyTorch-lightning⚡️ and Transformers🤗 that lets you quickly train your T5 models.

Quickly train T5 models in just 3 lines of code + ONNX support simpleT5 is built on top of PyTorch-lightning ⚡️ and Transformers 🤗 that lets you quic

Shivanand Roy 220 Dec 30, 2022
Pangu-Alpha for Transformers

Pangu-Alpha for Transformers Usage Download MindSpore FP32 weights for GPU from here to data/Pangu-alpha_2.6B.ckpt Activate MindSpore environment and

One 5 Oct 01, 2022
The aim of this task is to predict someone's English proficiency based on a text input.

English_proficiency_prediction_NLP The aim of this task is to predict someone's English proficiency based on a text input. Using the The NICT JLE Corp

1 Dec 13, 2021
Malaya-Speech is a Speech-Toolkit library for bahasa Malaysia, powered by Deep Learning Tensorflow.

Malaya-Speech is a Speech-Toolkit library for bahasa Malaysia, powered by Deep Learning Tensorflow. Documentation Proper documentation is available at

HUSEIN ZOLKEPLI 151 Jan 05, 2023