Difference between revisions of "Language/Multiple-languages/Culture/Text-Processing-Tools"

From Polyglot Club WIKI
Jump to navigation Jump to search
 
(61 intermediate revisions by 3 users not shown)
Line 1: Line 1:
[[Category:Computer-Knowledge]]
[[Category:Computer-Knowledge]]
{{Multiple-languages-flag}}


In some languages, words are not separated by spaces, for example: Chinese, Japanese, Lao, Thai. In Vietnamese, spaces are used to divide syllables instead of words. This brings about difficulties for computer programs like [https://vocabhunter.github.io/ VocabHunter], [https://github.com/jeffkowalski/gritz gritz] and [https://github.com/zg/text-memorize text-memorize], where words are detected only with spaces.
In this lesson, several useful linguistic tools useful for common language learners are discussed. They are not always accurate, so keep in mind.


The solution is called “[https://en.wikipedia.org/wiki/Text_segmentation#Word_segmentation word segmentation]”, which detects words and insert spaces in between. Sounds like easy, but they have to deal with ambiguities and unknown words including proper names, the time and accuracy are both to be considered. It can be based on the dictionary or machine learning.
Many of the tools introduced are written in Python, which is an important language in machine learning and easy to learn.


Here are free and open-source tools to do it:
If you don't know Python, please try this:
 
https://www.youtube.com/watch?v=_uQrJ0TkZlc
 
In progress.
 
== Diacritisation ==
In Arabic writing system, diacritics indicate the accents, but they are often omitted for writing fluently. The process of restoring diacritics is called diacritisation.
 
Arabic:
* Arabycia https://github.com/mohabmes/Arabycia
* Farasa https://github.com/MagedSaeed/farasapy
* Mishkal https://sourceforge.net/projects/mishkal/
* Pipeline-diacritizer https://github.com/Hamza5/Pipeline-diacritizer
* Shakkala https://github.com/Barqawiz/Shakkala
* Shakkelha https://github.com/AliOsm/shakkelha
 
== Lemmatisation ==
When you search a word in inflected form, the dictionary program can show you the result as lemma, during which the lemmatisation is done.
 
multiple languages:
* CST's lemmatiser https://www.cst.dk/online/lemmatiser/
* Pattern https://github.com/clips/pattern
* Simplemma https://github.com/adbar/simplemma
* TextBlob https://textblob.readthedocs.io/
 
English:
* LemmInflect https://github.com/bjascob/LemmInflect
* Natural Language Toolkit https://www.nltk.org/
 
German:
* GermaLemma https://github.com/WZBSocialScienceCenter/germalemma
 
Hungarian:
* HuSpaCy https://github.com/huspacy/huspacy
 
Persian:
* Hazm https://github.com/roshan-research/hazm
 
Turkish:
* Zeyrek https://github.com/obulat/zeyrek
 
== Pitch-Accent Marking ==
In Japanese and other languages, the pitch-accent is important on distinguishing different words. They are unwritten and required.
 
Japanese:
* Prosody Tutor Suzuki-kun http://www.gavo.t.u-tokyo.ac.jp/ojad/phrasing/index
* tdmelodic https://github.com/PKSHATechnology-Research/tdmelodic
 
== Stress Marking ==
In Russian and other languages, the stress is important on distinguishing different words. They are usually omitted.
 
Russian:
* RussianGram https://russiangram.com/
* Russian Stress Finder https://www.readyrussian.org/WebApps/StressFinder/
 
== Transcription ==
Some languages are written in more than one writing systems. This tool converts them from one to another.
 
Chinese:
* Chinese-Tools.com https://www.chinese-tools.com/tools/converter-simptrad.html
* ChineseConverter.com https://www.chineseconverter.com/en/convert/simplified-to-traditional
* hanzi2reading https://github.com/bdon/hanzi2reading
* OMGChinese.com https://www.omgchinese.com/tools/chinese-simplified-traditional-converter
 
== Part of Speech Tagging ==
It tags words in the sentence with parts of speech. Some of them can draw parse trees.
 
Multiple languages:
* CoreNLP https://github.com/stanfordnlp/CoreNLP
* Natural Language Toolkit https://www.nltk.org/
* spaCy https://spacy.io/
* Stanford Log-linear Part-Of-Speech Tagger https://nlp.stanford.edu/software/tagger.shtml
 
Arabic:
* Arabycia https://github.com/mohabmes/Arabycia
 
Chinese:
* FoolNLTK https://github.com/rockyzhengwu/FoolNLTK
* FudanNLP https://github.com/FudanNLP/fnlp
* HanLP https://github.com/hankcs/HanLP
* LAC https://github.com/baidu/lac
* LTP https://github.com/HIT-SCIR/ltp
* SnowNLP https://github.com/isnowfy/snownlp
* pkuseg https://github.com/lancopku/pkuseg-python
* pyhanlp https://github.com/hankcs/pyhanlp
* THULAC https://github.com/thunlp/THULAC-Python
 
Japanese:
* janome https://github.com/mocobeta/janome
* Juman++ https://github.com/ku-nlp/jumanpp
* Kagome https://github.com/ikawaha/kagome
* Kuromoji https://github.com/atilika/kuromoji / https://github.com/takuyaa/kuromoji.js/
* KyTea http://www.phontron.com/kytea/
* MeCab https://taku910.github.io/mecab/
* nagisa https://github.com/taishi-i/nagisa
* Sudachi https://github.com/WorksApplications/Sudachi / https://github.com/WorksApplications/SudachiPy
 
Thai:
* PyThaiNLP https://github.com/PyThaiNLP/pythainlp
* SynThai https://github.com/KrakenAI/SynThai
* TLTK https://pypi.org/project/tltk/
 
Vietnamese:
* JVnSegmenter http://jvnsegmenter.sourceforge.net/
* VnCoreNLP https://github.com/vncorenlp/VnCoreNLP
 
== Romanisation ==
multiple languages:
* Translit https://translit.cc/
 
Iranian Persian:
* Behnevis: easy farsi transliteration (pinglish) editor https://behnevis.com/en/
 
Japanese:
* NihongoDera - Romaji Converter https://nihongodera.com/tools/romaji-converter
 
Korean:
* 한국어/로마자 변환기 http://roman.cs.pusan.ac.kr/
 
Mandarin Chinese:
* Chinese Romanization Converter https://chinese.gratis/tools/zhuyin/
 
Standard Arabic:
* Romanize Arabic ALA-LC http://romanize-arabic.camel-lab.com/
 
Thai:
* thai-language.com Romanize an Arbitrary Thai Word http://thai-language.com/?nav=dictionary&anyxlit=1
* Phonetic transliteration of Thai https://www.thailit.com/transliterate.php
 
== Word Segmentation ==
In some languages, words are not separated by spaces, for example: Chinese, Japanese, Khmer, Lao, Thai. In Vietnamese, spaces are used to divide syllables instead of words. This brings about difficulties for computer programs like [https://vocabhunter.github.io/ VocabHunter], [https://github.com/jeffkowalski/gritz gritz] and [https://github.com/zg/text-memorize text-memorize], where words are detected only with spaces.
 
The solution is called “[https://en.wikipedia.org/wiki/Text_segmentation#Word_segmentation word segmentation]”, which detects words and insert spaces in between or put the segmented words into a list.
 
Burmese, Khmer, Lao, Thai:
* Chamkho https://codeberg.org/mekong-lang/chamkho
 
Burmese:
* Myan-word-breaker https://github.com/stevenay/myan-word-breaker


Chinese:
Chinese:
* Ansj https://github.com/NLPchina/ansj_seg
* Ansj https://github.com/NLPchina/ansj_seg
* CoreNLP https://github.com/stanfordnlp/CoreNLP
* FoolNLTK https://github.com/rockyzhengwu/FoolNLTK
* FoolNLTK https://github.com/rockyzhengwu/FoolNLTK
* FudanNLP https://github.com/FudanNLP/fnlp
* FudanNLP https://github.com/FudanNLP/fnlp
Line 30: Line 169:
* nagisa https://github.com/taishi-i/nagisa
* nagisa https://github.com/taishi-i/nagisa
* Sudachi https://github.com/WorksApplications/Sudachi / https://github.com/WorksApplications/SudachiPy
* Sudachi https://github.com/WorksApplications/Sudachi / https://github.com/WorksApplications/SudachiPy
Lao:
* Lao Word-Segmentation https://github.com/frankxayachack/LaoWordSegmentation


Thai:
Thai:
Line 44: Line 186:
* DongDu https://github.com/rockkhuya/DongDu
* DongDu https://github.com/rockkhuya/DongDu
* JVnSegmenter http://jvnsegmenter.sourceforge.net/
* JVnSegmenter http://jvnsegmenter.sourceforge.net/
* Roy_VnTokenizer https://github.com/roy-a/Roy_VnTokenizer
* VietSeg https://github.com/manhtai/vietseg
* VietSeg https://github.com/manhtai/vietseg
* VnCoreNLP https://github.com/vncorenlp/VnCoreNLP
* VnCoreNLP https://github.com/vncorenlp/VnCoreNLP


Many of them are written in Python, which is an important language in machine learning. It's very easy to use: just create a blank “.py” file, write a line to import from the library, write a line to segment the text, write a line to save the result.
==Other Lessons==
 
* [[Language/Multiple-languages/Culture/Internet-Dictionaries|Internet Dictionaries]]
If you don't know Python, please try this:
* [[Language/Multiple-languages/Culture/Astrology-in-different-Cultures-and-Languages|Astrology in different Cultures and Languages]]
 
* [[Language/Multiple-languages/Culture/How-to-make-a-TSV-file|How to make a TSV file]]
<youtube>_uQrJ0TkZlc</youtube>
* [[Language/Multiple-languages/Culture/Texts-and-Audios-under-a-Public-License|Texts and Audios under a Public License]]
* [[Language/Multiple-languages/Culture/Calendar-and-Clock|Calendar and Clock]]
* [[Language/Multiple-languages/Culture/Online-Specialized-Dictionaries|Online Specialized Dictionaries]]
* [[Language/Multiple-languages/Culture/Similar-Sayings|Similar Sayings]]
* [[Language/Multiple-languages/Culture/Elements-of-Traditional-Architectures:-Western-Europe|Elements of Traditional Architectures: Western Europe]]
* [[Language/Multiple-languages/Culture/Helpful-Anki-Shared-Decks|Helpful Anki Shared Decks]]
* [[Language/Multiple-languages/Culture/Internet-resources-for-learning-specific-languages|Internet resources for learning specific languages]]
<span links></span>

Latest revision as of 13:50, 16 February 2024

Multiple-languages-flag-polyglotclub.jpg

In this lesson, several useful linguistic tools useful for common language learners are discussed. They are not always accurate, so keep in mind.

Many of the tools introduced are written in Python, which is an important language in machine learning and easy to learn.

If you don't know Python, please try this:

https://www.youtube.com/watch?v=_uQrJ0TkZlc

In progress.

Diacritisation[edit | edit source]

In Arabic writing system, diacritics indicate the accents, but they are often omitted for writing fluently. The process of restoring diacritics is called diacritisation.

Arabic:

Lemmatisation[edit | edit source]

When you search a word in inflected form, the dictionary program can show you the result as lemma, during which the lemmatisation is done.

multiple languages:

English:

German:

Hungarian:

Persian:

Turkish:

Pitch-Accent Marking[edit | edit source]

In Japanese and other languages, the pitch-accent is important on distinguishing different words. They are unwritten and required.

Japanese:

Stress Marking[edit | edit source]

In Russian and other languages, the stress is important on distinguishing different words. They are usually omitted.

Russian:

Transcription[edit | edit source]

Some languages are written in more than one writing systems. This tool converts them from one to another.

Chinese:

Part of Speech Tagging[edit | edit source]

It tags words in the sentence with parts of speech. Some of them can draw parse trees.

Multiple languages:

Arabic:

Chinese:

Japanese:

Thai:

Vietnamese:

Romanisation[edit | edit source]

multiple languages:

Iranian Persian:

Japanese:

Korean:

Mandarin Chinese:

Standard Arabic:

Thai:

Word Segmentation[edit | edit source]

In some languages, words are not separated by spaces, for example: Chinese, Japanese, Khmer, Lao, Thai. In Vietnamese, spaces are used to divide syllables instead of words. This brings about difficulties for computer programs like VocabHunter, gritz and text-memorize, where words are detected only with spaces.

The solution is called “word segmentation”, which detects words and insert spaces in between or put the segmented words into a list.

Burmese, Khmer, Lao, Thai:

Burmese:

Chinese:

Japanese:

Lao:

Thai:

Vietnamese:

Other Lessons[edit | edit source]

Retrieved from "https://polyglotclub.com/wiki/index.php?title=Language/Multiple-languages/Culture/Text-Processing-Tools&oldid=291086"