- Conversational AI and Customer Service
What are the capabilities available to tackle the issues and opportunities in customer service? It’s no secret that Machine Learning (where computers are given real-world examples of data to learn from, and they can then apply what they’ve learnt to […] - Customer self-service is hard too
Done well, customer self-service offers a very attractive, low cost, low friction option for those many customers who prefer to engage in this way. It can be a great experience for a customer, getting what they need at a time […] - Customer Service is hard
By that, we really mean great customer service is hard. Customer relationships can be expensive to establish and maintain, but are critical, especially for a commodity product or service where customer service is the only differentiator or cost to serve is a big component of price. Complexity grows […] - We need to talk about search
Search in Help & Support could be so much better. The way many companies organise the Help & Support pages on their websites feels more like an afterthought than part of a customer experience strategy. The onus […] - Re-think your metrics
How conversational solutions can change your key metrics and the way you look at them. The only consistent truth about customers is that they want what they need, quickly and efficiently, at a time that suits them […] - Covid-19 and NLP
The Coronavirus pandemic and the Covid-19 illness have shone a light on the quality of information that is accessible and in particular the capacity for social media (a primary source for many) to spread disinformation. In some […] - Can NLP enhance RPA?
RPA is a pretty hot topic in the world of task automation, but the term is often misunderstood – mostly thanks to the vendor’s marketing teams. The image of a workforce of capable robots is an appealing […] - We love messagingOften, the best kind of customer service is silent running, a service that delivers exactly what the customer expects when they expect it – with no ambiguities or interruptions. Clearly, however, that’s not always possible, products and services can be complex to deliver, may involve external parties, may be vulnerable to poor data quality, or to things a customer may inadvertently do.
- Multi-label Text Classification using BERT – The Mighty Transformer
The past year has ushered in an exciting age for Natural Language Processing using deep neural networks. Research in the field of using pre-trained models have resulted in massive leap in state-of-the-art results for many of the […] - Train and Deploy the Mighty BERT based NLP models using FastBert and Amazon SageMaker
FastBert — The story so far… In my earlier introduction to FastBert, I described it as a library that will allow developers and data scientists to train and deploy BERT based models for NLP tasks beginning with Text […] - Introducing FastBert — A simple Deep Learning library for BERT Models
BERT What? The little Sesame Street muppet has taken the world of Natural Language Processing by storm and the storm is picking up speed. We have seen a number of NLP problems solved by neural network architectures built on […]