All Machine Learning (ML) engines that work with text can benefit from a solid linguistic background. If they are working in a multilingual environment, the need of a good lexicon (with forms, lemmas and attributes) is overwhelming. Even so, basic features such as Word Embeddings hugely improve when enriched with linguistic knowledge, and if this is not usually applied, is because of a lack of linguists working for ML companies.
When we talk about the usefulness of chatbots, we sometimes look at it as a black or white matter. Yet, the issue is not whether chatbots are useful or not, it’s rather how useful they are, and whether it is worth keeping them.
We have shown in previous posts why Synthetic Training Data is the best way to boost the accuracy of any chatbot, and the solution to the most important problems of chatbots nowadays: data scarcity, namely, the lack of accurate and useful training data for the problems chatbots want to address.
Do you know Amazon Connect? It’s a new platform created by Amazon —and built on AWS— that allows you to have your own Contact Center in the cloud, without having to get all the infrastructure that usual contact centers need. The philosophy is “Contact Center as a Service”, and Amazon is not the only one to implement it, but it’s actually one of the most interesting ones.
A few days ago we talked about how chatbots didn’t prove to be the revolution many of us expected. As we saw, one of the problems was related to expectations: chatbots were expected to be a magic wand that would solve everything. Yet, this doesn’t mean chatbots are not extremely useful when applied in the right environments and with the right goals in mind. We’ll present some cases of useful chatbots in the next weeks.
The company CB Insights has recently published a document named “Lessons From The Failed Chatbot Revolution”. This ominous title reveals a hard truth: chatbots have not been the revolution we expected.