Kylie Resources


Blog

To Build a Smarter Chatbot, First Teach It a Second Language

This blog post was originally posted on MIT Technology Review by Will Knight From Alexa and Siri to countless chatbots and automated customer support lines, computers are gradually learning to talk. The only trouble is they are still very easily confused. A research team at Salesforce has come up with a clever way to improve the performance of many modern language programs—teaching an algorithm to speak another language before training it to do other tasks.

Formulating an A.I. Strategy

Evaluating artificial intelligence in the enterprise can seem like a daunting task. The Kylie.ai team has worked with several leading organizations and has learned key insights in how to approach evaluating A.I. The following points can provide guidance and best practices in how to formulate an A.I. strategy.

Posted by josh@kylie.ai (Josh Adragna) on 10/2/17

Topics: Artificial Intelligence

The Beginner’s Guide to Text Vectorization

This blog post was originally posted on MonkeyLearn by Rodrigo Stecanella Since the beginning of the brief history of Natural Language Processing (NLP), there has been the need to transform text into something a machine can understand. That is, transforming text into a meaningful vector (or array) of numbers. The de-facto standard way of doing this in the pre-deep learning era was to use a bag of words approach.

Posted by Divya Susarla on 9/27/17

Topics: Machine Learning, natural language processing, text vectorization

Evaluating A.I. for Customer Support

Business leaders are becoming more keen to evaluate A.I. solutions. Based on our conversations in the market and being an A.I. provider, here is a list of things to consider when evaluating A.I for customer support.

Posted by Divya Susarla on 9/26/17

Topics: Artificial Intelligence, Customer Support


Library

Go Live in
90 Days.

Kylie.ai leads the industry in deployment time. We understand that every moment wasted equals lost opportunity. With Kylie.ai, get fully ramped up in less than 90 days.