Coding chatbots in node.js

Bots are a new way to interface with services and businesses. In today’s landscape, there’s Alexa, Facebook Messenger, Slack and more. Let’s see how we can code and test chat bots efficiently using natural language tools.

Transcript

1. @kahwee Coding chatbots in node.js
2. @kahwee Hi, I’m KahWee
3. • @kahwee • JavaScript for the past 5 years • Work for Tremor Video in San Francisco • Responsible for We Build SG chatbot • Likes sushi
4. @kahwee What is a chatbot? A chatbot is designed to perform a task via a chat user interface which is typically text enabled
5. @kahwee Why make a chatbot? • Reduce proximity between customers and businesses • Think personal assistants such as Cortana and Amazon Echo • Think chat messaging interfaces such as Facebook Messenger and Kik
6. @kahwee Why make a chatbot? • Businesses are competing on customer’s attention span over other businesses • ComScore found that average Americans devote half their app time to a single app.
8. @kahwee @TODO List ! Receiving messages from chat service " Comprehending the user’s input # Responding to the user
9. @kahwee ! Receiving messages from
 chat service How to integrate with chat services
10. @kahwee Using requestb.in https://requestb.in/
11. @kahwee ’s outgoing webhook
15. @kahwee Facebook Messenger’s webhook
16. @kahwee Facebook has an additional subscription step
17. @kahwee s
18. @kahwee s
19. @kahwee s c
20. @kahwee { "object": "page", "entry": [ { "id": "309202066131176", "time": 1479910134831, "messaging": [ { "sender": { "id": “1328417810563062" }, "recipient": { "id": “309202066131176" }, "timestamp": 1479910134741, "message": { "mid": "mid.1479910134741:99abab3941", "seq": 4, "text": "Hello How are you doing today?" } } ] } ] }
21. @kahwee Local development using localtunnel and nodemon
22. @kahwee Using localtunnel and nodemon • localtunnel • https://localtunnel.github.io/www/ • Lets you test and develop locally • nodemon • Automatically restarts on change
23. @kahwee Live demo https://github.com/kahwee/ranka-jsconfasia
24. @kahwee " Comprehending the user’s input
25. @kahwee “Book an appointment tomorrow at 4 PM” Using the above as an example
26. @kahwee “Book an appointment tomorrow at 4 PM” • The easiest way to determine the intent is to use rule-based filters on the current application • Example use case — Doctor’s appointment service • Only 2 main functions 1. getAppointments() 2. bookAppointment(datetime)
27. @kahwee Regex!
28. @kahwee /book an appointment/i "Book an appointment tomorrow at 4 PM".match(/book an appointment/i)
29. @kahwee /(book).*(appointment)/i "Book appointment tomorrow at 4 PM".match(/ (book).*(appointment)/i)
30. @kahwee /(book).*(appointment)/i "Book me an appointment tomorrow at 4 PM".match(/ (book).*(appointment)/i)
31. @kahwee /(book|reserve).*(appointment)/i "Reserve my appointment tomorrow at 4 PM".match(/(book| reserve).*(appointment)/i)
32. @kahwee /(arrange|book|reserve).*(appointment)/i "Arrange me an appointment tomorrow at 4 PM".match(/(arrange| book|reserve).*(appointment)/i)
33. @kahwee “Book an appointment tomorrow at 4 PM” We determined we need to use bookAppointment(datetime)
34. @kahwee “Book an appointment tomorrow at 4 PM” • How do we get the parameter “tomorrow at 4 PM”? • Regex isn’t as straightforward any more • There’s A Package For That ™
35. @kahwee Using simple NLP tools
36. @kahwee Using simple NLP tools • We are going to use nlp_compromise which has a parts of speech (POS) tagger • https://github.com/nlp-compromise/nlp_compromise • A POS Tagger is a piece of software that reads text and assigns parts of speech to each word or other token based on both its definition and its context — i.e., its relationship with adjacent and related words in a phrase, sentence, or paragraph. (Wikipedia) There’s A Package For That ™
37. @kahwee I have a pen Parse “I have a pen” with
 nlp_compromise const nlp = require('nlp')
 nlp.sentence('I have a pen').terms.forEach((t) => {
 console.log(t)
 })
38. @kahwee I have a pen Person { whitespace: { preceding: '', trailing: ' ' }, text: 'i', normal: 'i', expansion: null, reasoning: [ 'lexicon_pass', 'is_person' ], pos: { Noun: true, Person: true, Pronoun: true }, tag: 'Person', honourific: null, firstName: null, middleName: null, lastName: null },
39. @kahwee I have a pen Verb { whitespace: { preceding: '', trailing: ' ' }, text: 'have', normal: 'have', expansion: null, reasoning: [ 'lexicon_pass' ], pos: { Verb: true, Infinitive: true }, tag: 'Infinitive' }
40. @kahwee I have a pen Term { whitespace: { preceding: '', trailing: ' ' }, text: 'a', normal: 'a', expansion: null, reasoning: [ 'lexicon_pass' ], pos: { Determiner: true }, tag: 'Determiner' },
41. @kahwee I have a pen Noun { whitespace: { preceding: '', trailing: '' }, text: 'pen', normal: 'pen', expansion: null, reasoning: [ 'fallback' ], pos: { Noun: true }, tag: 'Noun' }
42. @kahwee I have an Person { whitespace: { preceding: '', trailing: ' ' }, text: 'i', normal: 'i', expansion: null, reasoning: [ 'lexicon_pass', 'is_person' ], pos: { Noun: true, Person: true, Pronoun: true }, tag: 'Person', honourific: null, firstName: null, middleName: null, lastName: null },
43. @kahwee I have an Verb { whitespace: { preceding: '', trailing: ' ' }, text: 'have', normal: 'have', expansion: null, reasoning: [ 'lexicon_pass' ], pos: { Verb: true, Infinitive: true }, tag: 'Infinitive' }
44. @kahwee I have an Term { whitespace: { preceding: '', trailing: ' ' }, text: 'a', normal: 'a', expansion: null, reasoning: [ 'lexicon_pass' ], pos: { Determiner: true }, tag: 'Determiner' },
45. @kahwee I have an Term { whitespace: { preceding: '', trailing: '' }, text: '', normal: '', expansion: null, reasoning: [], pos: {}, tag: '?' }
46. @kahwee I have an const gemoji = require('gemoji') console.log(gemoji.unicode[‘']) { description: 'red apple', names: [ 'apple' ], tags: [], name: 'apple', emoji: '' } There’s A Package For That ™
47. @kahwee Initial pass with nlp_compromise • Using nlp_compromise, • Parse “Book an appointment tomorrow at 4 PM” through nlp_compromise
48. @kahwee Book an appointment tomorrow at 4 PM Noun { whitespace: { preceding: '', trailing: ' ' }, text: 'Book', normal: 'book', expansion: null, reasoning: [ 'fallback' ], pos: { Noun: true }, tag: 'Noun' }
49. @kahwee Book an appointment tomorrow at 4 PM Term { whitespace: { preceding: '', trailing: ' ' }, text: 'an', normal: 'an', expansion: null, reasoning: [ 'lexicon_pass' ], pos: { Determiner: true }, tag: 'Determiner' },
50. @kahwee Book an appointment tomorrow at 4 PM Noun { whitespace: { preceding: '', trailing: ' ' }, text: 'appointment', normal: 'appointment', expansion: null, reasoning: [ 'fallback' ], pos: { Noun: true }, tag: 'Noun' },
51. @kahwee Book an appointment tomorrow at 4 PM _Date { whitespace: { preceding: '', trailing: '' }, text: 'tomorrow at 4 PM', normal: 'tomorrow at 4 pm', expansion: null, reasoning: [ 'lexicon_pass', 'lexicon_pass', 'Date-Preposition-Date' ], pos: { Noun: true, Date: true }, tag: 'Date', data: { year: null, month: null, day: null } } ]
52. @kahwee Book an appointment tomorrow at 4 PM Returns “2016-11-21T02:00:00.000Z” Passed through chrono-node There’s A Package For That ™
53. @kahwee Figuring out the date and time Use `chrono-node` const chrono = require(‘chrono-node') const parsed = chrono.parse('feb 23 to mar 2’) console.log(parsed[0].start.date()) // 2017-02-23T20:00:00.000Z console.log(parsed[0].end.date()) // 2017-03-02T20:00:00.000Z
54. @kahwee # Responding to the user
55. @kahwee General rules of thumb • Be succinct • Be friendly • Respect the medium • Handle errors
56. @kahwee Be succinct • Mobile messaging apps are limited by space. The shorter the bot responses are, the better. • Remember emojis are valid responses too! ✅
57. @kahwee Be friendly • Use pronouns like I and You. • Greetings, apologizing and thank you • Remember to greet back • It’s okay to say “Sorry I don’t understand” • Use active instead of passive voice. “Your flight has been booked” is not as good as “I booked your flight.” • Be humble and polite so people won’t be frustrated
58. @kahwee Respect the medium Know what kind of response the messaging API supports. For example, Facebook Messenger supports: • Text • Emoji • Location • Buttons
59. @kahwee Respect the medium • Format using “underscore.string” • toSentence(["jQuery", "Mootools", “Prototype"])
 // => "jQuery, Mootools and Prototype” • prune("Hello, cruel world", 15)
 // => "Hello, cruel..." There’s A Package For That ™
60. @kahwee Respect the medium • Giphy uses buttons in Slack
61. @kahwee Respect the medium • Poncho uses a “Send Location” button that users can tap on instead of typing a city name or postal code in Facebook Messenger
62. @kahwee Respect the medium • We Build SG uses generic templates in Facebook Messenger.
63. @kahwee Respect the medium • Use “ranka” for added expressivity • https://github.com/kahwee/ranka There’s A Package For That ™
64. @kahwee Handle errors “To err is human, to stderr program.”
65. @kahwee Problems faced when building bots 1. Choosing what to build is hard 2. You are encroaching into a personal space such as Facebook Messenger. 3. Every chat messaging system is a medium that can have special characteristics hence different APIs
66. @kahwee Conversational vs Structured text • Conversational text • Less predictable, potentially open-ended • Requires a complex rule-based system or machine learning capabilities
67. Humani: Jessie’s Story • Example of conversational chatbot • By PullString
68. @kahwee Conversational vs Structured text • Structured text • More predictable • Limited functionality
69. We Build SG • Example of structured chatbot • Built by me and We Build SG’s API • Try asking about “upcoming events” to We Build SG
70. @kahwee Sometimes coding it yourself isn’t the right solution
71. @kahwee Bot builders services • Octane AI • api.ai • KeyReply • PullString
72. @kahwee Machine learning and NLP services • luis.ai • wit.ai • api.ai
73. @kahwee Thanks • Spencer Kelly • Spencer Yang • Junshu Okamoto • Sayanee Basu
74. @kahwee Thanks • Source code for the afternoon: • https://github.com/kahwee/ranka-jsconfasia • We Build SG chatbot: • https://github.com/webuildsg/bot • Ranka: • https://github.com/kahwee/ranka