nlp

nlp / Word2Vector / 0.1.1

README.md

Introduction

This algorithm returns the vector representation of given words in a high-dimensional word embedding model.

Usage

Input

ParameterDescription
wordsA list of words in your given language
languageThe language code you want to use (default=en)
modelThe model you want to use (default=fasttext)
datasetThe dataset the model was trained on (default=ccwiki)

Output

ParameterDescription
wordsVector representation of the given word(s)

Examples

Example 1.

  • Parameter 1: An English word
  • Parameter 2: English as the selected language

Input:

{
	"words": "awesome",
	"language": "en"
}

Output:

{
  "words": [
    {
      "awesome": [
        0.033457573503255844,
        -0.012811683118343352,
        .
        .
        .
        -0.09583839029073717,
        -0.0779857486486435
      ]
    }
  ]
}

Example 2.

  • Parameter 1: Two Turkish words
  • Parameter 2: Turkish as the selected language
  • Parameter 3: Use fasttext as a model

Input:

{
	"words": ["elma", "armut"],
	"language": "tr",
	"model": "fasttext"
}

Output:

{
  "words": [
    {
      "elma": [
        -0.05182312801480293,
        0.10309629887342452,
        .
        .
        .
        0.061265796422958374,
        0.12890876829624176
      ]
    },
    {
      "armut": [
        0.06453978270292282,
        0.033210113644599915,
        .
        .
        .
        -0.031189830973744392,
        0.0567447692155838
      ]
    }
  ]
}

Supported Models & Languages

Currently only the following models & languages are supported:

NoModelDatasetLanguageCode
1fasttextCommon Crawl & WikipediaAfrikaansaf
2fasttextCommon Crawl & WikipediaAlbaniansq
3fasttextCommon Crawl & WikipediaAlemannicals
4fasttextCommon Crawl & WikipediaAmharicam
5fasttextCommon Crawl & WikipediaArabicar
6fasttextCommon Crawl & WikipediaAragonesean
7fasttextCommon Crawl & WikipediaArmenianhy
8fasttextCommon Crawl & WikipediaAssameseas
9fasttextCommon Crawl & WikipediaAsturianast
10fasttextCommon Crawl & WikipediaAzerbaijaniaz
11fasttextCommon Crawl & WikipediaBashkirba
12fasttextCommon Crawl & WikipediaBasqueeu
13fasttextCommon Crawl & WikipediaBavarianbar
14fasttextCommon Crawl & WikipediaBelarusianbe
15fasttextCommon Crawl & WikipediaBengalibn
16fasttextCommon Crawl & WikipediaBiharibh
17fasttextCommon Crawl & WikipediaBishnupriya Manipuribpy
18fasttextCommon Crawl & WikipediaBosnianbs
19fasttextCommon Crawl & WikipediaBretonbr
20fasttextCommon Crawl & WikipediaBulgarianbg
21fasttextCommon Crawl & WikipediaBurmesemy
22fasttextCommon Crawl & WikipediaCatalanca
23fasttextCommon Crawl & WikipediaCebuanoceb
24fasttextCommon Crawl & WikipediaCentral Bicolanobcl
25fasttextCommon Crawl & WikipediaChechence
26fasttextCommon Crawl & WikipediaChinesezh
27fasttextCommon Crawl & WikipediaChuvashcv
28fasttextCommon Crawl & WikipediaCorsicanco
29fasttextCommon Crawl & WikipediaCroatianhr
30fasttextCommon Crawl & WikipediaCzechcs
31fasttextCommon Crawl & WikipediaDanishda
32fasttextCommon Crawl & WikipediaDivehidv
33fasttextCommon Crawl & WikipediaDutchnl
34fasttextCommon Crawl & WikipediaEastern Punjabipa
35fasttextCommon Crawl & WikipediaEgyptian Arabicarz
36fasttextCommon Crawl & WikipediaEmilian-Romagnoleml
37fasttextCommon Crawl & WikipediaEnglishen
38fasttextCommon Crawl & WikipediaErzyamyv
39fasttextCommon Crawl & WikipediaEsperantoeo
40fasttextCommon Crawl & WikipediaEstonianet
41fasttextCommon Crawl & WikipediaFiji Hindihif
42fasttextCommon Crawl & WikipediaFinnishfi
43fasttextCommon Crawl & WikipediaFrenchfr
44fasttextCommon Crawl & WikipediaGaliciangl
45fasttextCommon Crawl & WikipediaGeorgianka
46fasttextCommon Crawl & WikipediaGermande
47fasttextCommon Crawl & WikipediaGoan Konkanigom
48fasttextCommon Crawl & WikipediaGreekel
49fasttextCommon Crawl & WikipediaGujaratigu
50fasttextCommon Crawl & WikipediaHaitianht
51fasttextCommon Crawl & WikipediaHebrewhe
52fasttextCommon Crawl & WikipediaHill Marimrj
53fasttextCommon Crawl & WikipediaHindihi
54fasttextCommon Crawl & WikipediaHungarianhu
55fasttextCommon Crawl & WikipediaIcelandicis
56fasttextCommon Crawl & WikipediaIdoio
57fasttextCommon Crawl & WikipediaIlokanoilo
58fasttextCommon Crawl & WikipediaIndonesianid
59fasttextCommon Crawl & WikipediaInterlinguaia
60fasttextCommon Crawl & WikipediaIrishga
61fasttextCommon Crawl & WikipediaItalianit
62fasttextCommon Crawl & WikipediaJapaneseja
63fasttextCommon Crawl & WikipediaJavanesejv
64fasttextCommon Crawl & WikipediaKannadakn
65fasttextCommon Crawl & WikipediaKapampanganpam
66fasttextCommon Crawl & WikipediaKazakhkk
67fasttextCommon Crawl & WikipediaKhmerkm
68fasttextCommon Crawl & WikipediaKirghizky
69fasttextCommon Crawl & WikipediaKoreanko
70fasttextCommon Crawl & WikipediaKurdish (Kurmanji)ku
71fasttextCommon Crawl & WikipediaKurdish (Sorani)ckb
72fasttextCommon Crawl & WikipediaLatinla
73fasttextCommon Crawl & WikipediaLatvianlv
74fasttextCommon Crawl & WikipediaLimburgishli
75fasttextCommon Crawl & WikipediaLithuanianlt
76fasttextCommon Crawl & WikipediaLombardlmo
77fasttextCommon Crawl & WikipediaLow Saxonnds
78fasttextCommon Crawl & WikipediaLuxembourgishlb
79fasttextCommon Crawl & WikipediaMacedonianmk
80fasttextCommon Crawl & WikipediaMaithilimai
81fasttextCommon Crawl & WikipediaMalagasymg
82fasttextCommon Crawl & WikipediaMalayms
83fasttextCommon Crawl & WikipediaMalayalamml
84fasttextCommon Crawl & WikipediaMaltesemt
85fasttextCommon Crawl & WikipediaManxgv
86fasttextCommon Crawl & WikipediaMarathimr
87fasttextCommon Crawl & WikipediaMazandaranimzn
88fasttextCommon Crawl & WikipediaMeadow Marimhr
89fasttextCommon Crawl & WikipediaMinangkabaumin
90fasttextCommon Crawl & WikipediaMingrelianxmf
91fasttextCommon Crawl & WikipediaMirandesemwl
92fasttextCommon Crawl & WikipediaMongolianmn
93fasttextCommon Crawl & WikipediaNahuatlnah
94fasttextCommon Crawl & WikipediaNeapolitannap
95fasttextCommon Crawl & WikipediaNepaline
96fasttextCommon Crawl & WikipediaNewarnew
97fasttextCommon Crawl & WikipediaNorth Frisianfrr
98fasttextCommon Crawl & WikipediaNorthern Sothonso
99fasttextCommon Crawl & WikipediaNorwegian (Bokmål)no
100fasttextCommon Crawl & WikipediaNorwegian (Nynorsk)nn
101fasttextCommon Crawl & WikipediaOccitanoc
102fasttextCommon Crawl & WikipediaOriyaor
103fasttextCommon Crawl & WikipediaOssetianos
104fasttextCommon Crawl & WikipediaPalatinate Germanpfl
105fasttextCommon Crawl & WikipediaPashtops
106fasttextCommon Crawl & WikipediaPersianfa
107fasttextCommon Crawl & WikipediaPiedmontesepms
108fasttextCommon Crawl & WikipediaPolishpl
109fasttextCommon Crawl & WikipediaPortuguesept
110fasttextCommon Crawl & WikipediaQuechuaqu
111fasttextCommon Crawl & WikipediaRomanianro
112fasttextCommon Crawl & WikipediaRomanshrm
113fasttextCommon Crawl & WikipediaRussianru
114fasttextCommon Crawl & WikipediaSakhasah
115fasttextCommon Crawl & WikipediaSanskritsa
116fasttextCommon Crawl & WikipediaSardiniansc
117fasttextCommon Crawl & WikipediaScotssco
118fasttextCommon Crawl & WikipediaScottish Gaelicgd
119fasttextCommon Crawl & WikipediaSerbiansr
120fasttextCommon Crawl & WikipediaSerbo-Croatiansh
121fasttextCommon Crawl & WikipediaSicilianscn
122fasttextCommon Crawl & WikipediaSindhisd
123fasttextCommon Crawl & WikipediaSinhalesesi
124fasttextCommon Crawl & WikipediaSlovaksk
125fasttextCommon Crawl & WikipediaSloveniansl
126fasttextCommon Crawl & WikipediaSomaliso
127fasttextCommon Crawl & WikipediaSouthern Azerbaijaniazb
128fasttextCommon Crawl & WikipediaSpanishes
129fasttextCommon Crawl & WikipediaSundanesesu
130fasttextCommon Crawl & WikipediaSwahilisw
131fasttextCommon Crawl & WikipediaSwedishsv
132fasttextCommon Crawl & WikipediaTagalogtl
133fasttextCommon Crawl & WikipediaTajiktg
134fasttextCommon Crawl & WikipediaTamilta
135fasttextCommon Crawl & WikipediaTatartt
136fasttextCommon Crawl & WikipediaTelugute
137fasttextCommon Crawl & WikipediaThaith
138fasttextCommon Crawl & WikipediaTibetanbo
139fasttextCommon Crawl & WikipediaTurkishtr
140fasttextCommon Crawl & WikipediaTurkmentk
141fasttextCommon Crawl & WikipediaUkrainianuk
142fasttextCommon Crawl & WikipediaUpper Sorbianhsb
143fasttextCommon Crawl & WikipediaUrduur
144fasttextCommon Crawl & WikipediaUyghurug
145fasttextCommon Crawl & WikipediaUzbekuz
146fasttextCommon Crawl & WikipediaVenetianvec
147fasttextCommon Crawl & WikipediaVietnamesevi
148fasttextCommon Crawl & WikipediaVolapükvo
149fasttextCommon Crawl & WikipediaWalloonwa
150fasttextCommon Crawl & WikipediaWaraywar
151fasttextCommon Crawl & WikipediaWelshcy
152fasttextCommon Crawl & WikipediaWest Flemishvls
153fasttextCommon Crawl & WikipediaWest Frisianfy
154fasttextCommon Crawl & WikipediaWestern Punjabipnb
155fasttextCommon Crawl & WikipediaYiddishyi
156fasttextCommon Crawl & WikipediaYorubayo
157fasttextCommon Crawl & WikipediaZazakidiq
158fasttextCommon Crawl & WikipediaZeelandiczea