Using Rasa NLU for entities extraction (NER)
Rasa is an open source library for building conversational interfaces, most commonly called “chatbots”. Building a good chatbot is not an easy task and people at Rasa knows it, that’s why their library contains a lot of different components working together. One of these components is the NLU (Natural Language Understanding) that resulted to be […]
Usando Rasa para extraer entidades (NER)
Rasa es una librería open source para construir interfaces conversacionales, más comunmente llamadas “chatbots”. Crear un chatbot que funcione realmente bien no es tarea fácil y la gente de Rasa lo sabe, por lo que su librería contiene muchos componentes que en conjunto permiten crear buenas experiencias conversacionales. Uno de esos componentes es el de […]
Detecting taxis from my balcony
[DISCLAIMER] This is a post from 2017 that I’ve recently translated from Spanish to English. [/DISCLAIMER] I’m doing the Deep Learning for Coders MOOC from fast.ai and the exercise in the first week consists on using a script to detect dogs and cats from several images. It’s always nice to apply what you learn in […]
A few resources to get into Deep Learning
Before making some recommendations I’d like to mention that I don’t have the absolute truth, this is simply a path that resonates with me because my personality is geared towards more practical resources. I usually like to delve into theory after I know the basics. Now that I made that clear, these are some resources […]
I have a small dataset…so what?
It’s widely known that one of the higher barriers to train a predictive model using Deep Learning is the availability of a large and proper labeled dataset as it usually carries a high time labeling cost to get it. So we have two high cost tasks right here and before getting to the fancy stage […]
Detección de fraudes con ML desde cero
Hace unas semanas me pidieron un pequeño informe (que no lleve mucho tiempo) a alto nivel de como implementaría la funcionalidad de detección de fraudes usando Machine Learning. Mi aclaración fue de que no soy un experto en el mundo de detección de fraudes y por lo tanto que mi enfoque puede no ser el […]
NLP techniques and the balance between model accuracy and explainability
If you’re working on a NLP related task, you’ll need to decide which approach to take. Before starting building the code a project structure, it’s important for you to define the specific goals of the project in terms of explainability and accuracy. Nowadays the NLP techniques that can offer more accuracy are the ones with […]
Traditional vs. AI software projects: dealing with uncertainty
You have to be prepared to deal with a lot of uncertainty if you want to work on Artificial Intelligence projects. You can estimate and plan a traditional software project, but most importantly, you know that sooner or later, with more or less difficulty, you will end up getting the project built. It’s a deterministic […]
Spreading the data bias virus
Nowadays there is a growing use of Deep Learning (DL) to build systems for machine decision making. DL is a powerful technology but it currently has a big limitation, you need a lot of (most times) manually labeled data in order to train the AI model. That’s why most of the time we want to […]
The centralization of the data powering the AI software
Artificial Intelligence powered software is everywhere and it’s spreading massively, so it’s a pretty safe guess to say that in a short time span, even small unconnected businesses are going to rely on AI algorithms to run their daily operations. If they refuse they could give a competitive advantage to similar businesses that use AI […]