[](https://pypi.org/project/multicombo/)
# MultiCOMBO
Multilingual POS-Tagger and Dependency-Parser with [COMBO-pytorch](https://gitlab.clarin-pl.eu/syntactic-tools/combo) and [spaCy](https://spacy.io)
## Basic usage
```py
>>> import multicombo
>>> nlp=multicombo.load()
>>> doc=nlp('Who plays "La vie en rose"?')
>>> print(multicombo.to_conllu(doc))
# text = Who plays "La vie en rose"?
1 Who _ PRON _ PronType=Int 2 nsubj _ Translit=who
2 plays _ VERB _ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 0 root _ _
3 " _ PUNCT _ _ 5 punct _ SpaceAfter=No
4 La _ DET _ Definite=Def|Gender=Fem|Number=Sing|PronType=Art 5 det _ Translit=la
5 vie _ NOUN _ Gender=Fem|Number=Sing 2 obj _ _
6 en _ ADP _ _ 7 case _ _
7 rose _ NOUN _ Number=Sing 5 nmod _ SpaceAfter=No
8 " _ PUNCT _ _ 5 punct _ SpaceAfter=No
9 ? _ PUNCT _ _ 2 punct _ SpaceAfter=No
>>> import deplacy
>>> deplacy.render(doc)
Who PRON <════════════╗ nsubj
plays VERB ═══════════╗═╝═╗ ROOT
" PUNCT <══════╗ ║ ║ punct
La DET <════╗ ║ ║ ║ det
vie NOUN ═══╗═╝═╝═╗<╝ ║ obj
en ADP <╗ ║ ║ ║ case
rose NOUN ═╝<╝ ║ ║ nmod
" PUNCT <════════╝ ║ punct
? PUNCT <══════════════╝ punct
>>> deplacy.serve(doc)
http://127.0.0.1:5000
```
`multicombo.load(lang="xx")` loads spaCy Language pipeline with [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) and `spacy.lang.xx.MultiLanguage` tokenizer. Other language specific tokenizers can be loaded with the option `lang`, while several languages require additional packages:
* `lang="ja"` Japanese requires [SudachiPy](https://pypi.org/project/SudachiPy/) and [SudachiDict-core](https://pypi.org/project/SudachiDict-core/).
* `lang="th"` Thai requires [PyThaiNLP](https://pypi.org/project/pythainlp/).
* `lang="vi"` Vietnamese requires [pyvi](https://pypi.org/project/pyvi/).
## Installation for Linux
```sh
pip3 install allennlp@git+https://github.com/allenai/allennlp
pip3 install 'transformers<4.31'
pip3 install multicombo
```
## Installation for Cygwin64
Make sure to get `python37-devel` `python37-pip` `python37-cython` `python37-numpy` `python37-cffi` `gcc-g++` `mingw64-x86_64-gcc-g++` `gcc-fortran` `git` `curl` `make` `cmake` `libopenblas` `liblapack-devel` `libhdf5-devel` `libfreetype-devel` `libuv-devel` packages, and then:
```sh
curl -L https://raw.githubusercontent.com/KoichiYasuoka/UniDic-COMBO/master/cygwin64.sh | sh
pip3.7 install multicombo
```
## Installation for Jupyter Notebook (Google Colaboratory)
Try [notebook](https://colab.research.google.com/github/KoichiYasuoka/MultiCOMBO/blob/main/multicombo.ipynb).
Raw data
{
"_id": null,
"home_page": "https://github.com/KoichiYasuoka/MultiCOMBO",
"name": "multicombo",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": null,
"keywords": "NLP Multilingual",
"author": "Koichi Yasuoka",
"author_email": "yasuoka@kanji.zinbun.kyoto-u.ac.jp",
"download_url": null,
"platform": null,
"description": "[](https://pypi.org/project/multicombo/)\n\n# MultiCOMBO\n\nMultilingual POS-Tagger and Dependency-Parser with [COMBO-pytorch](https://gitlab.clarin-pl.eu/syntactic-tools/combo) and [spaCy](https://spacy.io)\n\n## Basic usage\n\n```py\n>>> import multicombo\n>>> nlp=multicombo.load()\n>>> doc=nlp('Who plays \"La vie en rose\"?')\n>>> print(multicombo.to_conllu(doc))\n# text = Who plays \"La vie en rose\"?\n1\tWho\t_\tPRON\t_\tPronType=Int\t2\tnsubj\t_\tTranslit=who\n2\tplays\t_\tVERB\t_\tMood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin\t0\troot\t_\t_\n3\t\"\t_\tPUNCT\t_\t_\t5\tpunct\t_\tSpaceAfter=No\n4\tLa\t_\tDET\t_\tDefinite=Def|Gender=Fem|Number=Sing|PronType=Art\t5\tdet\t_\tTranslit=la\n5\tvie\t_\tNOUN\t_\tGender=Fem|Number=Sing\t2\tobj\t_\t_\n6\ten\t_\tADP\t_\t_\t7\tcase\t_\t_\n7\trose\t_\tNOUN\t_\tNumber=Sing\t5\tnmod\t_\tSpaceAfter=No\n8\t\"\t_\tPUNCT\t_\t_\t5\tpunct\t_\tSpaceAfter=No\n9\t?\t_\tPUNCT\t_\t_\t2\tpunct\t_\tSpaceAfter=No\n\n>>> import deplacy\n>>> deplacy.render(doc)\nWho PRON <\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2557 nsubj\nplays VERB \u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2557\u2550\u255d\u2550\u2557 ROOT\n\" PUNCT <\u2550\u2550\u2550\u2550\u2550\u2550\u2557 \u2551 \u2551 punct\nLa DET <\u2550\u2550\u2550\u2550\u2557 \u2551 \u2551 \u2551 det\nvie NOUN \u2550\u2550\u2550\u2557\u2550\u255d\u2550\u255d\u2550\u2557<\u255d \u2551 obj\nen ADP <\u2557 \u2551 \u2551 \u2551 case\nrose NOUN \u2550\u255d<\u255d \u2551 \u2551 nmod\n\" PUNCT <\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u255d \u2551 punct\n? PUNCT <\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u255d punct\n\n>>> deplacy.serve(doc)\nhttp://127.0.0.1:5000\n```\n\n`multicombo.load(lang=\"xx\")` loads spaCy Language pipeline with [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) and `spacy.lang.xx.MultiLanguage` tokenizer. Other language specific tokenizers can be loaded with the option `lang`, while several languages require additional packages:\n* `lang=\"ja\"` Japanese requires [SudachiPy](https://pypi.org/project/SudachiPy/) and [SudachiDict-core](https://pypi.org/project/SudachiDict-core/).\n* `lang=\"th\"` Thai requires [PyThaiNLP](https://pypi.org/project/pythainlp/).\n* `lang=\"vi\"` Vietnamese requires [pyvi](https://pypi.org/project/pyvi/).\n\n## Installation for Linux\n\n```sh\npip3 install allennlp@git+https://github.com/allenai/allennlp\npip3 install 'transformers<4.31'\npip3 install multicombo\n```\n\n## Installation for Cygwin64\n\nMake sure to get `python37-devel` `python37-pip` `python37-cython` `python37-numpy` `python37-cffi` `gcc-g++` `mingw64-x86_64-gcc-g++` `gcc-fortran` `git` `curl` `make` `cmake` `libopenblas` `liblapack-devel` `libhdf5-devel` `libfreetype-devel` `libuv-devel` packages, and then:\n```sh\ncurl -L https://raw.githubusercontent.com/KoichiYasuoka/UniDic-COMBO/master/cygwin64.sh | sh\npip3.7 install multicombo\n```\n\n## Installation for Jupyter Notebook (Google Colaboratory)\n\nTry [notebook](https://colab.research.google.com/github/KoichiYasuoka/MultiCOMBO/blob/main/multicombo.ipynb).\n\n",
"bugtrack_url": null,
"license": "GPL",
"summary": "Multilingual POS-tagger and Dependency-parser",
"version": "0.8.6",
"project_urls": {
"COMBO-pytorch": "https://gitlab.clarin-pl.eu/syntactic-tools/combo",
"Homepage": "https://github.com/KoichiYasuoka/MultiCOMBO",
"Source": "https://github.com/KoichiYasuoka/MultiCOMBO",
"Tracker": "https://github.com/KoichiYasuoka/MultiCOMBO/issues"
},
"split_keywords": [
"nlp",
"multilingual"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "1e8aaf1e954c43c3ccdc17a8ed5d936e691675941594e61c115ceee1e0e35b9b",
"md5": "b742619e8935ef42114a051fc09da393",
"sha256": "ed024eac37c93d61ddc4bb777ee565815b4ad6defe1c7fdc4146d1234fda5936"
},
"downloads": -1,
"filename": "multicombo-0.8.6-py3-none-any.whl",
"has_sig": false,
"md5_digest": "b742619e8935ef42114a051fc09da393",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.6",
"size": 16779,
"upload_time": "2025-07-13T08:22:12",
"upload_time_iso_8601": "2025-07-13T08:22:12.035114Z",
"url": "https://files.pythonhosted.org/packages/1e/8a/af1e954c43c3ccdc17a8ed5d936e691675941594e61c115ceee1e0e35b9b/multicombo-0.8.6-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-13 08:22:12",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "KoichiYasuoka",
"github_project": "MultiCOMBO",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "multicombo"
}
JSON
