In the last COP25 Climate Summit held in Madrid. Many subjects were being discussed on the matter of a possible climate crisis, and how to face it.
Has Machine Learning (ML) and Natural Language Processing (NLP) something to say about it? Surprisingly, yes, it does!
In this blog we will discuss three ways of doing your chatbot evaluation by using:
One of the flaws of usual training data generation is that, when you ask somebody to manually create training data for you, they will make an effort to write these sentences correctly, following the spelling and punctuation norms of your language. Even if some errors appear, they will be minimal, because they are trying to do things right —this is, to provide “orthographically right” sentences.
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.
