In May 2019, the Collision Conference took place in Toronto for the first time, and we couldn’t miss it! It was a great opportunity to meet amazing people, learn from great companies and showcase our own capabilities.
Attending the first day’s talks at the Collision center stage
AI solutions naturally attract attention
Lots of interest interest in our conversational AI
Crowdsourced data can often be inconsistent, messy or downright wrong
We all like something for nothing, that’s why open source software is so popular. (It’s also why the Pirate Bay exists). But sometimes things that seem too good to be true are just that.
Repustate is in the text analytics game which means we needs lots and lots of data to model certain characteristics of written text. We need common words, grammar constructs, human-annotated corpora of text etc. to make our various language models work as quickly and as well as they do.
We recently embarked on the next phase of our text analytics adventure: semantic analysis. Semantic analysis the process of taking arbitrary text and assigning meaning to the individual, relevant components. For example, being able to identify “apple” as a fruit in the sentence “I went apple picking yesterday” but to identify “Apple’ the company when saying “I can’t wait for the new Apple product announcement” (note: even though I used title case for the latter example, casing should not matter)
The main difference is in the linguistic complexity.
People express themselves differently when they speak compared to when they type. When we speak we use more sentences and we make our sentences longer.
As a result a voice bot needs to have better AI compared to a chatbot, in order to handle a conversation and deliver the same customer experience.
If your business model allows it, is better to start with a chatbot and add a voice bot on top of it.
This way you can gradually increase the complexity of your AI without compromising on your customer experience.