Skip to main content

Pre-trained Entities


Open In Collab Run in Postman

Entity Code: pre-trained

To help you get started we have 36 entity extractors you can use off-the-shelf.

Entity Catalog

EntityDescription
personPeople, including fictional
locationNon-GPE (Geo-Political Entity) locations, mountain ranges, bodies of water
miscellaneousMiscellaneous
norpNationalities or religious or political groups
facilityBuildings, airports, highways, bridges, etc
organizationCompanies, agencies, institutions, etc.
geo-political-entitiesCountries, cities, states
productVehicles, weapons, foods, etc. (Not services)
eventNamed hurricanes, battles, wars, sports events, etc
work-of-artTitles of books, songs, etc.
lawNamed documents made into laws
languageAny named language
dateAbsolute or relative dates or periods
timeTimes smaller than a day
percentPercentage (including “%”)
moneyMonetary values, including unit
quantityMeasurements, as of weight or distance
ordinal“first”, “second”
cardinalNumerals that do not fall under another type
movementGlobal movements
pet-namePet names
phonePhone numbers
title-affix'Mr.' or 'Shri' or 'Mahatma' or 'Chakravarti' (as in 'Chakravarti Rajagopalachari')
designation'Chairman' (as in 'Chairman Mao') or just 'The Chair' or 'President' (as in 'President Bush') or 'Baadshaah' (as in 'Baadshaah Akbar')
abbreviation'IBM' (or I.B.M.) or 'CRF' or 'APJ' or 'KKK' or 'VHP'
brand'Fanta' or 'Windows' or 'Linux' or 'Thumbs Up' or 'HP Laserjet 5M'
title-object'The Seven Year Itch' or 'American Beauty' or '1984' (as in '1984 by George Orwell') or 'One Hundred Years of Solitude'
measure‘Five kilos', 'three days', 'seven years'
terms'Horticulture', 'Conditional Random Fields', 'Sociolinguistics', 'The Butterfly Effect'
credit-card-numberCredit card numbers like 4111-1111-1111-1111
distanceDistance, e.g., 6 miles
durationTime duration, e.g., 3 mins
emailEmail, e.g., a@b.com
temperatureTemperature, e.g., 80F
urlURLs, e.g., www.a.com, https://hello.com
volumeVolume, e.g., 4 gallons
pnrPNR codes

Entities by Language

Different languages support a different set of entities.

LanguageLanguage CodeEntities
Hindihiordinal phone person duration location money cardinal organization url email temperature
Telugutephone person location money cardinal organization url email
Swedishsvordinal person duration location event time distance cardinal organization
Finnishfilocation organization cardinal person
Arabicarordinal volume person duration location time cardinal organization quantity temperature
Catalancaordinal volume url duration money distance cardinal time temperature
Croatianhrordinal volume duration time distance cardinal quantity temperature
Czechcsdistance cardinal
Estonianetordinal person location organization cardinal
Hungarianhuordinal person duration location time cardinal organization
Irishgaordinal volume duration time distance cardinal temperature
Slovakskcardinal
Bulgarianbgordinal person duration location time distance cardinal organization
Turkishtrordinal volume person duration location time distance cardinal organization temperature
Ukrainianukduration ordinal time cardinal
Hebrewheordinal person duration location time cardinal organization
Indonesianidordinal person location organization cardinal
Koreankoordinal volume person duration location time distance cardinal organization quantity temperature
Vietnameseviordinal person duration location time cardinal organization
Bengalibnlocation organization cardinal person
Kannadakncardinal
Malayalammlordinal person location organization cardinal
Afrikaansaflocation organization cardinal person
Tamiltaordinal person location organization cardinal
Persianfalocation organization cardinal person
Danishdaordinal phone person location money time organization cardinal miscellaneous url email
Norwegian Bokmålnbordinal phone person location duration money time organization cardinal miscellaneous url email
Greekelordinal person product location event geo-political-entities duration time organization cardinal
Englishenvolume date money work-of-art cardinal quantity url email phone duration percent organization law language norp ordinal person product location event geo-political-entities time distance facility temperature
Chinesezhdate money work-of-art cardinal quantity duration percent organization law language norp ordinal person product location event geo-political-entities time distance facility temperature
Dutchnlvolume date money work-of-art cardinal quantity duration percent organization law language norp ordinal person product location event geo-political-entities time distance facility
Frenchfrordinal volume person location duration time distance organization cardinal quantity miscellaneous temperature
Germandeordinal volume person location duration time distance organization cardinal miscellaneous
Italianitordinal volume person location duration time distance organization cardinal miscellaneous temperature
Portugueseptordinal volume person location duration time distance organization cardinal quantity miscellaneous temperature
Polishplordinal person location geo-political-entities date time duration organization cardinal
Japanesejatitle-affix date money work-of-art cardinal quantity phone duration percent organization law language pet-name norp ordinal person product location event geo-political-entities time facility movement temperature
Romanianrovolume date money work-of-art cardinal quantity duration percent organization law language norp ordinal person product location event geo-political-entities time distance facility temperature
Russianruordinal volume person location duration time distance organization cardinal quantity
Spanishesordinal volume person location duration time distance organization cardinal quantity miscellaneous temperature
Lithuanianltproduct person location geo-political-entities time organization
Basqueeulocation organization person
Kazakhkklocation organization person
Marathimrlocation organization person
Urduurlocation organization person

List Pretrained Entities

You can access all available pre-trained entities using the CLI. Make sure to follow Getting started for CLI and then simply use the following command.

neuralspace nlu get-pretrained-entities -L "hi"

Refer to the table below to see all the input paramters for this command.

AttributeRequiredTypeDescription
--language or -LtruestrSet to the language you wish to see pre-trained entities for.
--search or -sfalsestrPass the text for which you wish to see related pre-trained entities.
--page-number or -p falseintSet to the page number you wish to go to.
--page-size or -PfalseintSet to the number of entities you wish to see in one page.
--entitiy-type or -TfalsestrSet to one of pre-trained, lookup, synonym, regex depending upon which type of entities you wish to access.

Pre-trained Entities in NLU Models

To use a pre-trained entities in your NLU models you will have to tag at least one training example with it. Additionally, you will have to set the entityType attribute of the entity to pre-trained.

note

Make sure the name of the entity you use matches one of the supported

Sample training example
{
"projectId": "YOUR-PROJECT-ID",
"language": "en",
"example": {
"intent": "set_alarm",
"text": "set an alarm for 25 minutes .",
"type": "train",
"entities": [
{
"entity": "time",
"value": "for 25 minutes",
"start": 13,
"end": 27,
"entityType": "pre-trained"
}
]
}
}