Tags » Natural Language Understanding

Thoughts on machine learning for customer service chatbots

I’m thinking out loud a bit about machine learning strategies for customer service chatbots. Bear with me. More question than answers, because some of the strategies I see, I just fail to understand. 431 more words

Customer Experience

Phrase Detectives caught me by surprise

I got 52% play Phrase Detective on Facebook. How could I get a PhD in Natural Language Processing?

Just kidding, I’m not worrying at all about graduation but just a bit surprised by some features of the game. 848 more words

Natural Language Understanding

Chatbot hypen

Det er lite tvil om at chatbot har fått mye oppmerksomhet, men med tanke på at 80% av kundekommunikasjon fortsatt foregår enten på telefon eller epost, så er det kanskje litt for tidlig å begynne med automatisering på en mindre brukt kanal som chat reellt sett oftest er. 276 more words


Word-level Language Modeling vs Character-level Language Modeling

Nowadays Character-Level Language Modeling gets a lots of attention for better Language Understanding Tasks. Here I simply describes a comparative understanding of Character-level and Word-level Language Understanding. 364 more words

Deep Learning

Manthan honored with Innovation Partner Award at AWS Partner Summit 2017

Manthan has won the Innovation Partner Award for the second consecutive year, at Amazon Web Services (AWS) India Partner Summit.

By combining AWS technologies with its expertise spanning descriptive and advanced analytics including forecasting, recommendations and causality, Manthan has created Maya, the world’s first AI-powered conversational platform for business analytics. 70 more words


Tips & Tricks for building a better LUIS model

Chatbots has become a ‘trend’ today. Everyone wants to attach a chatbot for their businesses. Either to the public facing phase or as the interfering interface of an internal business process. 814 more words


Notes on machine learning and exceptions

Statistical machine learning has been the de-facto standard in NLP research and practice. However, its very success might be hiding its the problems. One such problem is exceptions. 775 more words

Neural Networks