Tokenizer POS-tagger Lemmatizer and Dependency-parser for modern and contemporary Japanese with BERT models

These details have not been verified by PyPI

Project links

Project description

SuPar-UniDic

Tokenizer, POS-tagger, lemmatizer, and dependency-parser for modern and contemporary Japanese with BERT models.

Basic usage

>>> import suparunidic
>>> nlp=suparunidic.load()
>>> doc=nlp("太郎は花子が読んでいる本を次郎に渡した")
>>> print(type(doc))
<class 'spacy.tokens.doc.Doc'>
>>> print(suparunidic.to_conllu(doc))
1	太郎	タロウ	PROPN	名詞-固有名詞-人名-名	_	12	nsubj	_	SpaceAfter=No|Translit=タロー
2	は	は	ADP	助詞-係助詞	_	1	case	_	SpaceAfter=No|Translit=ワ
3	花子	ハナコ	PROPN	名詞-固有名詞-人名-名	_	5	nsubj	_	SpaceAfter=No|Translit=ハナコ
4	が	が	ADP	助詞-格助詞	_	3	case	_	SpaceAfter=No|Translit=ガ
5	読ん	読む	VERB	動詞-一般	_	8	acl	_	SpaceAfter=No|Translit=ヨン
6	で	て	SCONJ	助詞-接続助詞	_	5	mark	_	SpaceAfter=No|Translit=デ
7	いる	居る	AUX	動詞-非自立可能	_	5	aux	_	SpaceAfter=No|Translit=イル
8	本	本	NOUN	名詞-普通名詞-一般	_	12	obj	_	SpaceAfter=No|Translit=ホン
9	を	を	ADP	助詞-格助詞	_	8	case	_	SpaceAfter=No|Translit=オ
10	次郎	ジロウ	PROPN	名詞-固有名詞-人名-名	_	12	obl	_	SpaceAfter=No|Translit=ジロー
11	に	に	ADP	助詞-格助詞	_	10	case	_	SpaceAfter=No|Translit=ニ
12	渡し	渡す	VERB	動詞-一般	_	0	root	_	SpaceAfter=No|Translit=ワタシ
13	た	た	AUX	助動詞	_	12	aux	_	SpaceAfter=No|Translit=タ

>>> import deplacy
>>> deplacy.render(doc,Japanese=True)
太郎 PROPN ═╗<════════╗ nsubj(主語)
は   ADP   <╝         ║ case(格表示)
花子 PROPN ═╗<══╗     ║ nsubj(主語)
が   ADP   <╝   ║     ║ case(格表示)
読ん VERB  ═╗═╗═╝<╗   ║ acl(連体修飾節)
で   SCONJ <╝ ║   ║   ║ mark(標識)
いる AUX   <══╝   ║   ║ aux(動詞補助成分)
本   NOUN  ═╗═════╝<╗ ║ obj(目的語)
を   ADP   <╝       ║ ║ case(格表示)
次郎 PROPN ═╗<╗     ║ ║ obl(斜格補語)
に   ADP   <╝ ║     ║ ║ case(格表示)
渡し VERB  ═╗═╝═════╝═╝ ROOT(親)
た   AUX   <╝           aux(動詞補助成分)
>>> from deplacy.deprelja import deprelja
>>> for b in suparunidic.bunsetu_spans(doc):
...   for t in b.lefts:
...     print(suparunidic.bunsetu_span(t),"->",b,"("+deprelja[t.dep_]+")")
...
花子が -> 読んでいる (主語)
読んでいる -> 本を (連体修飾節)
太郎は -> 渡した (主語)
本を -> 渡した (目的語)
次郎に -> 渡した (斜格補語)

suparunidic.load(UniDic,BERT) loads a natural language processor pipeline, which uses UniDic for tokenizer POS-tagger and lemmatizer, then uses BERT for Biaffine dependency-parser of SuPar. Available UniDic options are:

UniDic="gendai" 現代書き言葉UniDic
UniDic="spoken" 現代話し言葉UniDic
UniDic="qkana" 旧仮名口語UniDic
UniDic="kindai" 近代文語UniDic
UniDic="kinsei" 近世口語（洒落本）UniDic
UniDic="kyogen" 中世口語（狂言）UniDic
UniDic="wakan" 中世文語（説話・随筆）UniDic
UniDic="wabun" 中古和文UniDic
UniDic="manyo" 上代（万葉集）UniDic
UniDic=None unidic-lite (default)

Available BERT options are:

BERT="bert-japanese-aozora6m3m-unidic32k-2m" from bert-japanese-aozora (default)
BERT="roberta-large-japanese-aozora" from roberta-large-japanese-aozora
BERT="roberta-large-japanese-aozora-char" from roberta-large-japanese-aozora-char
BERT="roberta-base-japanese-aozora" from roberta-base-japanese-aozora
BERT="roberta-base-japanese-aozora-char" from roberta-base-japanese-aozora-char
BERT="roberta-small-japanese-aozora" from roberta-small-japanese-aozora
BERT="roberta-small-japanese-aozora-char" from roberta-small-japanese-aozora-char
BERT="bert-base-japanese-char-extended" from bert-base-japanese-char-extended
BERT="bert-large-japanese-char-extended" from bert-large-japanese-char-extended
BERT="bert-base-japanese-char" from cl-tohoku (fugashi and ipadic required)
BERT="bert-base-japanese-whole-word-masking" from cl-tohoku (fugashi and ipadic required)
BERT="bert-large-japanese" from cl-tohoku (fugashi required)
BERT="bert-large-japanese-char" from cl-tohoku (fugashi required)
BERT="roberta-base-japanese" from nlp-waseda (SentencePiece required)
BERT="electra-base-japanese-discriminator" from izumi-lab (fugashi and ipadic required)
BERT="bert-small-japanese" from izumi-lab (fugashi and ipadic required)
BERT="electra-base-japanese-generator" from izumi-lab (fugashi and ipadic required)
BERT="japanese-roberta-base" from rinna (SentencePiece required)
BERT="albert-japanese-v2" from alinear-corp (SentencePiece required)
BERT="albert-base-japanese-v1" from ken11
BERT="electra-small-japanese-discriminator" from Cinnamon AI
BERT="electra-small-japanese-generator" from Cinnamon AI
BERT="ku-bert-japanese-large" from ku-bert-japanese
BERT="bert-base-ja-cased" from Geotrend
BERT="laboro-bert-japanese-large" from Laboro AI
BERT="nict-bert-base-japanese-100k" from NICT BERT
BERT="unihanlm-base" from microsoft/unihanlm-base
BERT="distilbert-base-japanese" from bandainamco-mirai

Installation for Linux

pip3 install suparunidic --user

Installation for Cygwin64

Make sure to get python37-devel python37-pip python37-cython python37-numpy python37-wheel gcc-g++ mingw64-x86_64-gcc-g++ git curl make cmake, and then:

curl -L https://raw.githubusercontent.com/KoichiYasuoka/CygTorch/master/installer/supar.sh | sh
pip3.7 install suparunidic

Benchmarks

Results of 舞姬/雪國/荒野より-Benchmarks

BERT="bert-japanese-aozora6m3m-unidic32k-2m"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	84.91	74.07	81.48
UniDic="kindai"	84.91	74.07	81.48
UniDic="kinsei"	74.07	64.29	71.43

雪國	LAS	MLAS	BLEX
UniDic="qkana"	85.71	78.43	74.51
UniDic="kindai"	81.42	74.51	70.59
UniDic="kinsei"	85.71	78.43	70.59

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	74.35	56.00	56.00
UniDic="kindai"	74.35	53.33	53.33
UniDic="kinsei"	71.88	50.67	50.67

BERT="roberta-large-japanese-aozora"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	75.47	58.18	65.45
UniDic="kindai"	75.47	58.18	65.45
UniDic="kinsei"	66.67	52.63	56.14

雪國	LAS	MLAS	BLEX
UniDic="qkana"	87.50	82.35	78.43
UniDic="kindai"	83.19	78.43	74.51
UniDic="kinsei"	87.50	82.35	74.51

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	80.63	64.94	59.74
UniDic="kindai"	80.63	62.34	57.14
UniDic="kinsei"	78.12	59.74	54.55

BERT="roberta-large-japanese-aozora-char"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	79.25	69.09	76.36
UniDic="kindai"	79.25	69.09	76.36
UniDic="kinsei"	68.52	59.65	63.16

雪國	LAS	MLAS	BLEX
UniDic="qkana"	85.71	78.43	74.51
UniDic="kindai"	81.42	74.51	70.59
UniDic="kinsei"	85.71	78.43	70.59

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	76.44	61.33	61.33
UniDic="kindai"	76.44	61.33	61.33
UniDic="kinsei"	72.92	56.00	56.00

BERT="roberta-base-japanese-aozora"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	79.25	65.45	72.73
UniDic="kindai"	79.25	65.45	72.73
UniDic="kinsei"	68.52	60.71	64.29

雪國	LAS	MLAS	BLEX
UniDic="qkana"	87.50	82.35	78.43
UniDic="kindai"	83.19	78.43	74.51
UniDic="kinsei"	87.50	82.35	74.51

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	76.44	58.67	61.33
UniDic="kindai"	76.44	56.00	58.67
UniDic="kinsei"	73.96	53.33	56.00

BERT="roberta-base-japanese-aozora-char"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	83.02	70.37	77.78
UniDic="kindai"	83.02	70.37	77.78
UniDic="kinsei"	74.07	65.45	69.09

雪國	LAS	MLAS	BLEX
UniDic="qkana"	85.71	78.43	74.51
UniDic="kindai"	81.42	74.51	70.59
UniDic="kinsei"	85.71	78.43	70.59

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	76.44	57.89	57.89
UniDic="kindai"	76.44	55.26	55.26
UniDic="kinsei"	73.96	52.63	52.63

BERT="roberta-small-japanese-aozora"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	83.02	72.73	76.36
UniDic="kindai"	83.02	72.73	76.36
UniDic="kinsei"	70.37	60.71	64.29

雪國	LAS	MLAS	BLEX
UniDic="qkana"	85.71	78.43	74.51
UniDic="kindai"	81.42	74.51	70.59
UniDic="kinsei"	85.71	78.43	70.59

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	74.35	56.00	56.00
UniDic="kindai"	74.35	53.33	53.33
UniDic="kinsei"	71.88	50.67	50.67

BERT="roberta-small-japanese-aozora-char"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	77.36	65.45	72.73
UniDic="kindai"	77.36	65.45	72.73
UniDic="kinsei"	70.37	59.65	63.16

雪國	LAS	MLAS	BLEX
UniDic="qkana"	85.71	78.43	74.51
UniDic="kindai"	81.42	74.51	70.59
UniDic="kinsei"	85.71	78.43	70.59

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	73.30	53.33	53.33
UniDic="kindai"	73.30	50.67	50.67
UniDic="kinsei"	70.83	48.00	48.00

BERT="bert-base-japanese-char-extended"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	81.13	72.73	76.36
UniDic="kindai"	81.13	72.73	76.36
UniDic="kinsei"	68.52	59.65	63.16

雪國	LAS	MLAS	BLEX
UniDic="qkana"	85.71	78.43	74.51
UniDic="kindai"	81.42	74.51	70.59
UniDic="kinsei"	85.71	78.43	70.59

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	75.39	56.00	56.00
UniDic="kindai"	75.39	53.33	53.33
UniDic="kinsei"	71.88	48.00	48.00

BERT="bert-large-japanese-char-extended"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	75.47	64.29	71.43
UniDic="kindai"	75.47	64.29	71.43
UniDic="kinsei"	64.81	55.17	62.07

雪國	LAS	MLAS	BLEX
UniDic="qkana"	85.71	78.43	74.51
UniDic="kindai"	81.42	74.51	70.59
UniDic="kinsei"	85.71	78.43	70.59

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	78.53	64.00	64.00
UniDic="kindai"	78.53	61.33	61.33
UniDic="kinsei"	76.04	58.67	58.67

BERT="bert-base-japanese-char"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	77.36	64.29	71.43
UniDic="kindai"	77.36	64.29	71.43
UniDic="kinsei"	66.67	55.17	58.62

雪國	LAS	MLAS	BLEX
UniDic="qkana"	78.57	72.00	68.00
UniDic="kindai"	74.34	68.00	64.00
UniDic="kinsei"	78.57	72.00	64.00

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	75.39	58.67	58.67
UniDic="kindai"	75.39	56.00	56.00
UniDic="kinsei"	72.92	53.33	53.33

BERT="bert-base-japanese-whole-word-masking"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	73.58	57.14	64.29
UniDic="kindai"	73.58	57.14	64.29
UniDic="kinsei"	64.81	51.72	55.17

雪國	LAS	MLAS	BLEX
UniDic="qkana"	85.71	82.35	78.43
UniDic="kindai"	76.11	73.08	69.23
UniDic="kinsei"	85.71	82.35	74.51

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	73.30	52.63	52.63
UniDic="kindai"	73.30	52.63	52.63
UniDic="kinsei"	69.79	50.00	50.00

BERT="bert-large-japanese"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	79.25	65.45	72.73
UniDic="kindai"	79.25	65.45	72.73
UniDic="kinsei"	68.52	56.14	59.65

雪國	LAS	MLAS	BLEX
UniDic="qkana"	78.57	76.92	73.08
UniDic="kindai"	74.34	73.08	69.23
UniDic="kinsei"	78.57	76.92	69.23

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	78.53	59.74	57.14
UniDic="kindai"	78.53	57.14	54.55
UniDic="kinsei"	77.08	54.55	51.95

BERT="bert-large-japanese-char"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	79.25	69.09	72.73
UniDic="kindai"	79.25	69.09	72.73
UniDic="kinsei"	68.52	59.65	63.16

雪國	LAS	MLAS	BLEX
UniDic="qkana"	80.36	70.59	70.59
UniDic="kindai"	76.11	66.67	66.67
UniDic="kinsei"	80.36	70.59	66.67

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	74.35	53.33	53.33
UniDic="kindai"	74.35	50.67	50.67
UniDic="kinsei"	71.88	48.00	48.00

BERT="roberta-base-japanese"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	83.02	72.73	76.36
UniDic="kindai"	83.02	72.73	76.36
UniDic="kinsei"	72.22	63.16	66.67

雪國	LAS	MLAS	BLEX
UniDic="qkana"	85.71	78.43	74.51
UniDic="kindai"	83.19	78.43	74.51
UniDic="kinsei"	85.71	78.43	70.59

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	72.25	51.35	51.35
UniDic="kindai"	72.25	51.35	51.35
UniDic="kinsei"	69.79	48.65	48.65

BERT="electra-base-japanese-discriminator"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	75.47	61.82	69.09
UniDic="kindai"	75.47	61.82	69.09
UniDic="kinsei"	64.81	52.63	56.14

雪國	LAS	MLAS	BLEX
UniDic="qkana"	87.50	82.35	78.43
UniDic="kindai"	83.19	78.43	74.51
UniDic="kinsei"	87.50	82.35	74.51

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	73.30	50.67	50.67
UniDic="kindai"	73.30	50.67	50.67
UniDic="kinsei"	70.83	48.00	48.00

BERT="bert-small-japanese"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	79.25	62.96	70.37
UniDic="kindai"	79.25	62.96	70.37
UniDic="kinsei"	70.37	57.14	60.71

雪國	LAS	MLAS	BLEX
UniDic="qkana"	76.79	73.08	69.23
UniDic="kindai"	72.57	69.23	65.38
UniDic="kinsei"	76.79	73.08	65.38

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	72.25	47.37	47.37
UniDic="kindai"	72.25	47.37	47.37
UniDic="kinsei"	69.79	42.67	45.33

BERT="electra-base-japanese-generator"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	77.36	64.29	71.43
UniDic="kindai"	77.36	64.29	71.43
UniDic="kinsei"	68.52	58.62	62.07

雪國	LAS	MLAS	BLEX
UniDic="qkana"	76.79	73.08	69.23
UniDic="kindai"	72.57	69.23	65.38
UniDic="kinsei"	76.79	73.08	65.38

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	69.11	45.33	45.33
UniDic="kindai"	69.11	45.33	45.33
UniDic="kinsei"	66.67	42.67	42.67

BERT="japanese-roberta-base"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	73.58	57.14	64.29
UniDic="kindai"	73.58	57.14	64.29
UniDic="kinsei"	64.81	51.72	55.17

雪國	LAS	MLAS	BLEX
UniDic="qkana"	87.50	82.35	78.43
UniDic="kindai"	83.19	78.43	74.51
UniDic="kinsei"	87.50	82.35	74.51

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	74.35	50.00	47.37
UniDic="kindai"	74.35	47.37	44.74
UniDic="kinsei"	71.88	44.74	42.11

BERT="albert-japanese-v2"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	77.36	64.29	71.43
UniDic="kindai"	77.36	64.29	71.43
UniDic="kinsei"	66.67	55.17	58.62

雪國	LAS	MLAS	BLEX
UniDic="qkana"	76.79	73.08	69.23
UniDic="kindai"	72.57	69.23	65.38
UniDic="kinsei"	76.79	73.08	65.38

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	73.30	51.95	49.35
UniDic="kindai"	73.30	49.35	46.75
UniDic="kinsei"	69.79	46.75	44.16

BERT="albert-base-japanese-v1"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	73.58	57.14	64.29
UniDic="kindai"	73.58	57.14	64.29
UniDic="kinsei"	64.81	51.72	55.17

雪國	LAS	MLAS	BLEX
UniDic="qkana"	76.79	73.08	69.23
UniDic="kindai"	74.34	69.23	65.38
UniDic="kinsei"	76.79	73.08	65.38

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	65.97	42.67	42.67
UniDic="kindai"	65.97	40.00	40.00
UniDic="kinsei"	64.58	39.47	39.47

BERT="electra-small-japanese-discriminator"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	73.58	57.14	64.29
UniDic="kindai"	73.58	57.14	64.29
UniDic="kinsei"	62.96	48.28	51.72

雪國	LAS	MLAS	BLEX
UniDic="qkana"	73.21	69.23	65.38
UniDic="kindai"	70.80	65.38	61.54
UniDic="kinsei"	73.21	69.23	61.54

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	74.35	50.00	47.37
UniDic="kindai"	74.35	50.00	47.37
UniDic="kinsei"	72.92	50.00	47.37

BERT="electra-small-japanese-generator"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	73.58	60.71	64.29
UniDic="kindai"	73.58	60.71	64.29
UniDic="kinsei"	66.67	55.17	58.62

雪國	LAS	MLAS	BLEX
UniDic="qkana"	73.21	69.23	65.38
UniDic="kindai"	70.80	65.38	61.54
UniDic="kinsei"	73.21	69.23	61.54

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	69.11	45.95	45.95
UniDic="kindai"	69.11	43.24	43.24
UniDic="kinsei"	66.67	40.54	40.54

BERT="ku-bert-japanese-large"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	77.36	65.45	72.73
UniDic="kindai"	77.36	65.45	72.73
UniDic="kinsei"	64.81	52.63	59.65

雪國	LAS	MLAS	BLEX
UniDic="qkana"	82.14	74.51	70.59
UniDic="kindai"	81.42	74.51	70.59
UniDic="kinsei"	82.14	74.51	66.67

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	62.83	39.47	42.11
UniDic="kindai"	62.83	36.84	39.47
UniDic="kinsei"	62.50	38.96	41.56

BERT="bert-base-ja-cased"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	73.58	58.18	65.45
UniDic="kindai"	73.58	58.18	65.45
UniDic="kinsei"	64.81	52.63	56.14

雪國	LAS	MLAS	BLEX
UniDic="qkana"	73.21	69.23	65.38
UniDic="kindai"	70.80	65.38	61.54
UniDic="kinsei"	73.21	69.23	61.54

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	63.87	41.56	44.16
UniDic="kindai"	63.87	38.96	41.56
UniDic="kinsei"	61.46	36.36	38.96

BERT="laboro-bert-japanese-large"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	71.70	56.14	63.16
UniDic="kindai"	71.70	56.14	63.16
UniDic="kinsei"	62.96	50.85	54.24

雪國	LAS	MLAS	BLEX
UniDic="qkana"	71.43	65.38	65.38
UniDic="kindai"	67.26	61.54	61.54
UniDic="kinsei"	71.43	65.38	61.54

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	67.02	42.67	42.67
UniDic="kindai"	67.02	40.00	40.00
UniDic="kinsei"	65.62	37.33	37.33

BERT="nict-bert-base-japanese-100k"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	67.92	49.12	52.63
UniDic="kindai"	67.92	49.12	52.63
UniDic="kinsei"	57.41	40.68	44.07

雪國	LAS	MLAS	BLEX
UniDic="qkana"	82.14	74.51	74.51
UniDic="kindai"	81.42	74.51	74.51
UniDic="kinsei"	82.14	74.51	70.59

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	68.06	41.10	43.84
UniDic="kindai"	68.06	38.36	41.10
UniDic="kinsei"	65.62	35.62	38.36

BERT="unihanlm-base"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	69.81	52.63	59.65
UniDic="kindai"	69.81	52.63	59.65
UniDic="kinsei"	61.11	47.46	50.85

雪國	LAS	MLAS	BLEX
UniDic="qkana"	85.71	78.43	78.43
UniDic="kindai"	79.65	70.59	70.59
UniDic="kinsei"	85.71	78.43	74.51

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	61.78	36.36	38.96
UniDic="kindai"	61.78	36.36	38.96
UniDic="kinsei"	60.42	36.36	38.96

BERT="distilbert-base-japanese"

舞姬	LAS	MLAS	BLEX
UniDic="qkana"	77.36	64.29	71.43
UniDic="kindai"	77.36	64.29	71.43
UniDic="kinsei"	68.52	58.62	62.07

雪國	LAS	MLAS	BLEX
UniDic="qkana"	73.21	69.23	65.38
UniDic="kindai"	70.80	65.38	61.54
UniDic="kinsei"	73.21	69.23	61.54

荒野より	LAS	MLAS	BLEX
UniDic="qkana"	63.87	34.67	40.00
UniDic="kindai"	63.87	32.00	37.33
UniDic="kinsei"	62.50	34.21	36.84

Author

Koichi Yasuoka (安岡孝一)

Project details

These details have not been verified by PyPI

Project links

Release history Release notifications | RSS feed

1.4.7

Feb 28, 2026

1.4.6

Jan 22, 2026

1.4.5

Aug 31, 2025

1.4.4

Aug 30, 2025

1.4.3

Mar 27, 2025

1.4.2

Jan 31, 2024

1.4.1

Oct 24, 2023

1.4.0

Sep 24, 2023

1.3.9

Apr 17, 2023

1.3.8

Jun 11, 2022

1.3.7

Jun 10, 2022

1.3.6

May 28, 2022

1.3.5

May 27, 2022

1.3.4

May 24, 2022

1.3.3

May 24, 2022

1.3.2

May 24, 2022

1.3.1

Apr 24, 2022

1.3.0

Apr 24, 2022

1.2.9

Apr 15, 2022

This version

1.2.8

Mar 14, 2022

1.2.7

Dec 31, 2021

1.2.6

Dec 31, 2021

1.2.5

Dec 31, 2021

1.2.4

Dec 31, 2021

1.2.3

Dec 27, 2021

1.2.2

Dec 25, 2021

1.2.1

Dec 25, 2021

1.2.0

Dec 23, 2021

1.1.9

Dec 23, 2021

1.1.8

Dec 21, 2021

1.1.7

Dec 21, 2021

1.1.6

Dec 20, 2021

1.1.5

Dec 20, 2021

1.1.4

Dec 18, 2021

1.1.3

Nov 23, 2021

1.1.2

Nov 22, 2021

1.1.1

Nov 7, 2021

1.1.0

Nov 4, 2021

1.0.9

Nov 4, 2021

1.0.8

Oct 26, 2021

1.0.7

Oct 24, 2021

1.0.6

Oct 24, 2021

1.0.5

Oct 24, 2021

1.0.4

Sep 4, 2021

1.0.3

Sep 4, 2021

1.0.2

Aug 31, 2021

1.0.1

Aug 31, 2021

1.0.0

Aug 27, 2021

0.9.9

Aug 27, 2021

0.9.8

Jul 9, 2021

0.9.7

Jun 19, 2021

0.9.6

Jun 4, 2021

0.9.5

Jun 4, 2021

0.9.4

Jun 2, 2021

0.9.3

May 3, 2021

0.9.2

Apr 30, 2021

0.9.1

Apr 30, 2021

0.9.0

Apr 29, 2021

0.8.9

Apr 27, 2021

0.8.8

Apr 15, 2021

0.8.7

Apr 15, 2021

0.8.6

Apr 10, 2021

0.8.5

Apr 8, 2021

0.8.4

Apr 4, 2021

0.8.3

Mar 27, 2021

0.8.2

Mar 27, 2021

0.8.1

Mar 24, 2021

0.8.0

Mar 17, 2021

0.7.9

Mar 16, 2021

0.7.8

Mar 16, 2021

0.7.6

Mar 11, 2021

0.7.4

Mar 11, 2021

0.7.3

Mar 10, 2021

0.7.2

Mar 10, 2021

0.7.0

Feb 23, 2021

0.6.9

Feb 23, 2021

0.6.8

Feb 23, 2021

0.6.7

Feb 23, 2021

0.6.6

Feb 22, 2021

0.6.5

Feb 22, 2021

0.6.4

Feb 22, 2021

0.6.3

Feb 22, 2021

0.6.2

Feb 22, 2021

0.6.1

Feb 22, 2021

0.6.0

Feb 22, 2021

0.5.4

Feb 22, 2021

0.5.3

Feb 22, 2021

0.5.2

Feb 21, 2021

0.5.1

Feb 21, 2021

0.5.0

Feb 21, 2021

0.4.5

Feb 21, 2021

0.4.4

Feb 21, 2021

0.4.3

Feb 21, 2021

0.4.2

Feb 21, 2021

0.4.1

Feb 21, 2021

0.4.0

Feb 21, 2021

0.3.0

Feb 21, 2021

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

suparunidic-1.2.8-py3-none-any.whl (993.6 kB view details)

Uploaded Mar 14, 2022 Python 3

File details

Details for the file suparunidic-1.2.8-py3-none-any.whl.

File metadata

Download URL: suparunidic-1.2.8-py3-none-any.whl
Upload date: Mar 14, 2022
Size: 993.6 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.25.1 setuptools/52.0.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.2

File hashes

Hashes for suparunidic-1.2.8-py3-none-any.whl
Algorithm	Hash digest
SHA256	`743d730fcb6e4bf6b7515cf0ea66a4f31da4255cb153b8131ceb4bfd1ed438fb`
MD5	`f79e7819de85ba393a0c8b25acc6614c`
BLAKE2b-256	`d8b550687a1818f2e2d0f1aeacf033afdf2a7ec568a2e9b731afa941fbf3dbdc`

See more details on using hashes here.

suparunidic 1.2.8

Navigation

Verified details

Maintainers

Unverified details

Project links

Meta

Classifiers

Project description

SuPar-UniDic

Basic usage

Installation for Linux

Installation for Cygwin64

Benchmarks

BERT="bert-japanese-aozora6m3m-unidic32k-2m"

BERT="roberta-large-japanese-aozora"

BERT="roberta-large-japanese-aozora-char"

BERT="roberta-base-japanese-aozora"

BERT="roberta-base-japanese-aozora-char"

BERT="roberta-small-japanese-aozora"

BERT="roberta-small-japanese-aozora-char"

BERT="bert-base-japanese-char-extended"

BERT="bert-large-japanese-char-extended"

BERT="bert-base-japanese-char"

BERT="bert-base-japanese-whole-word-masking"

BERT="bert-large-japanese"

BERT="bert-large-japanese-char"

BERT="roberta-base-japanese"

BERT="electra-base-japanese-discriminator"

BERT="bert-small-japanese"

BERT="electra-base-japanese-generator"

BERT="japanese-roberta-base"

BERT="albert-japanese-v2"

BERT="albert-base-japanese-v1"

BERT="electra-small-japanese-discriminator"

BERT="electra-small-japanese-generator"

BERT="ku-bert-japanese-large"

BERT="bert-base-ja-cased"

BERT="laboro-bert-japanese-large"

BERT="nict-bert-base-japanese-100k"

BERT="unihanlm-base"

BERT="distilbert-base-japanese"

Author

Project details

Verified details

Maintainers

Unverified details

Project links

Meta

Classifiers

Release history Release notifications | RSS feed

Download files

Source Distributions

Built Distribution

File details

File metadata

File hashes