In this blog we will discuss three ways of doing your chatbot evaluation by using:
- real world evaluation data
- synthetic data
- "in scope" or "out of scope" queries
One of the flaws of usual training data generation is that, when you ask somebody to manually create training data for you, they will make an effort to write these sentences correctly, following the spelling and punctuation norms of your language. Even if some errors appear, they will be minimal, because they are trying to do things right —this is, to provide “orthographically right” sentences.
A chatbot offers significant advantages: it allows your customer support to be omnichannel —i.e. customers will be able to approach you via written chat, voice chat, email, phone, etc.—; it will save you the costs of hiring many additional employees, while sparing you the need of training agents every time your product changes; your customers’ satisfaction will increase; finally, you will get more and more sales (because well-taken-care-of visitors tend to become loyal and regular customers).
Let’s repeat: more and more people (customers, or prospective customers) prefer eCommerce these days. They have learnt the comfort of buying from their home, without having to take their car or the public transport to personally go and buy at each store. As always, each option has its advantages and disadvantages, but eCommerce has become a common trend now.
These days we are talking about our partnership with Amazon Connect. But how can you benefit of it? We want to explain it now. Using our new AWS services for Amazon Connect is very simple.
A few days ago we announced our partnership with Amazon Connect. Today we'd like to give you more details about it. As a result of this partnership, Bitext is now offering the following three services: Instant LexBot, LexBot Booster and Custom LexBot. Let’s find out more details about them.