node-nlp how to extract email, phone, url? - node.js

Question

I'm using node nlp to extract the phone, url ,email etc. The sample code given was just an object in the help page. I don't know how to initialize the extract code. The read me for extraction url is https://github.com/axa-group/nlp.js/blob/master/docs/builtin-entity-extraction.md#ip-extraction
One of the sample in that page is given below.
Email extraction
It can identify and extract valid emails accounts, this works for any language.
"utterance": "My email is something#somehost.com please write me",
"entities": [
{
"start": 12,
"end": 33,
"len": 22,
"accuracy": 0.95,
"sourceText": "something#somehost.com",
"utteranceText": "something#somehost.com",
"entity": "email",
"resolution": {
"value": "something#somehost.com"
}
}
]
I have installed the npm and initialized like this
const { NlpManager } = require('node-nlp');
const manager = new NlpManager({ languages: ['en'] });
What must be the next steps(Need a sample code) to do the extractions?
The npm url is : https://www.npmjs.com/package/node-nlp

Answer 1

I will provide you an example code:
const { NlpManager } = require('node-nlp');
const manager = new NlpManager({ languages: ['en'] });
async function mainExtractEntities() {
const result = await manager.extractEntities('en', 'Are you able to identify that meh#meh.com is an email and moh#moh.com is another email so there are 2 emails?');
console.log(result);
}
async function mainFullExample() {
manager.addDocument('en', 'My mail is %email%', 'email');
manager.addDocument('en', 'My email is %email%', 'email');
manager.addDocument('en', 'Here you have my email: %email%', 'email');
manager.addDocument('en', 'Hello', 'greet');
manager.addDocument('en', 'Good morning', 'greet');
manager.addDocument('en', 'good afternoon', 'greet');
manager.addDocument('en', 'good evening', 'greet');
manager.addAnswer('en', 'email', 'Your email is {{email}}');
manager.addAnswer('en', 'greet', 'Hi!');
await manager.train();
let result = await manager.process('en', 'I think that my mail is meh#meh.com');
console.log(result);
result = await manager.process('en', 'Hello bot!');
console.log(result);
}
mainExtractEntities();
mainFullExample();
This will show in console:
[ { start: 30,
end: 40,
len: 11,
accuracy: 0.95,
sourceText: 'meh#meh.com',
utteranceText: 'meh#meh.com',
entity: 'email',
resolution: { value: 'meh#meh.com' } },
{ start: 58,
end: 68,
len: 11,
accuracy: 0.95,
sourceText: 'moh#moh.com',
utteranceText: 'moh#moh.com',
entity: 'email',
resolution: { value: 'moh#moh.com' } },
{ start: 100,
end: 100,
len: 1,
accuracy: 0.95,
sourceText: '2',
utteranceText: '2',
entity: 'number',
resolution: { strValue: '2', value: 2, subtype: 'integer' } } ]
{ locale: 'en',
localeIso2: 'en',
language: 'English',
utterance: 'I think that my mail is meh#meh.com',
classification:
[ { label: 'email', value: 0.9994852170204532 },
{ label: 'greet', value: 0.0005147829795467752 } ],
intent: 'email',
domain: 'default',
score: 0.9994852170204532,
entities:
[ { start: 24,
end: 34,
len: 11,
accuracy: 0.95,
sourceText: 'meh#meh.com',
utteranceText: 'meh#meh.com',
entity: 'email',
resolution: [Object] } ],
sentiment:
{ score: 0.25,
comparative: 0.027777777777777776,
vote: 'positive',
numWords: 9,
numHits: 1,
type: 'senticon',
language: 'en' },
srcAnswer: 'Your email is {{email}}',
answer: 'Your email is meh#meh.com' }
{ locale: 'en',
localeIso2: 'en',
language: 'English',
utterance: 'Hello bot!',
classification:
[ { label: 'greet', value: 0.8826839762075465 },
{ label: 'email', value: 0.1173160237924536 } ],
intent: 'greet',
domain: 'default',
score: 0.8826839762075465,
entities: [],
sentiment:
{ score: 0,
comparative: 0,
vote: 'neutral',
numWords: 2,
numHits: 0,
type: 'senticon',
language: 'en' },
srcAnswer: 'Hi!',
answer: 'Hi!' }
Important things to know:
You can omit the language in the extractEntities and process and pass undefined instead, that way the language will be guessed from your sentence to fit the best language of your NlpManger.
The email extraction works for any language. You have other entities more complex, like text numbers, that will be extracted only for some languages
The entity extraction is only one part, other interesting partes are the NLU classifier and the Natural Language Generation, you will see that the answer "Your email is {{email}}" is a template and the email is replaced with the extracted one from the conversation.