d

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore.

15 St Margarets, NY 10033
(+381) 11 123 4567
ouroffice@aware.com

 

KMF

Adaptive chatbot dialogs | Machine Learning

Most chatbots rely on pre-scripted dialog flows, built to meet a specific goal. Let’s take a simple example:

Bot:  how can I help?
User: I need a duplicate bank statement
Bot: ok which year?
User: 2020
Bot: which month?
User: may

Even this example is not quite as simple as it seems. What happens if the conversation goes like this:

Bot:  how can I help?
User: I need a duplicate bank statement for may 2020
Bot: ok which year?
User: i just told you

1. Chatbot Trends Report 2021

2. 4 DO’s and 3 DON’Ts for Training a Chatbot NLP Model

3. Concierge Bot: Handle Multiple Chatbots from One Chat Screen

4. An expert system: Conversational AI Vs Chatbots

So far so good. What happens if the conversation goes like this:

Bot:  how can I help?
User: I need a duplicate bank for the last month
Bot: ok which year?
User: this year of course

Let’s take another example, this time retail. Imagine we run a clothing store, and we want to recommend products to our customers. First we ask the user some questions to understand their wants. For this example we will assume we need to fill these “slots”:

  1. style
  2. brand
  3. fabric
  4. colour
  5. size
  6. price

Do we really need to capture 7 pieces of information before displaying some results? We run two risks:

  1. The dialog may be so long that the user gets bored and gives up.

Maybe we decide to focus on the attributes/slots that we absolutely need. Perhaps product type, price and size. After all, there’s not much point offering someone something they can’t afford or won’t fit.

Ideally we want to achieve three goals:

  1. Offer real value, beyond that which is achievable through other means (e.g. a website)
  2. Stimulate and retain the user’s interest (AIDA)
  • the time of the day
  • the device used
  • new vs repeat/loyal customer

Machine learning can help us here. During a “training” period we build the dialogs dynamically, trying different permutations of slots. Like split A/B testing on steroids. We record everything, including the time of day, drop off rate, conversions etc. This behavioural data can be used to build a machine learning model. This could be a simple regression model or something more sophisticated like a decision tree or ensemble model.

At a minimum our dialog flow should be smart enough to avoid asking redundant questions. We do this by filling multiple slots from each user response. We only prompt users for unfilled slots. Named Entity Recognition may not be enough. We may also need to also employ Part of Speech and Dependency Parsing for more complex concepts.

Credit: Source link

Previous Next
Close
Test Caption
Test Description goes like this