Published in Becoming Human: Artificial Intelligence Magazine·Jun 8Conversational AI at Ludicrous SpeedThe Problem Imagine that you have to build a Conversational AI for your company and deploy it in production. You talk with the CTO of your company and she shares with you that the company has more than 5 million subscribers on WeChat, and when a marketing campaign is launched, there are…NLP9 min read
Published in Planeta Chatbot : todo sobre los Chat bots, Voice apps e Inteligencia Artificial·Oct 23, 2020Empezando con NLP.jsDescubre el potencial de NLP.js un conjunto de más de 70 librerías de código abierto.NLP8 min read
Published in Just-Tech-IT·Sep 22, 2020Getting started with NLP.jsEver wanted to build a chatbot and encountered some blockers along the way relating to data privacy or supported languages? Do you wish to reduce chatbot response time or run them without an active data connection? If that’s the case or if you’re just curious and want to learn more…Chatbots7 min read
Published in Chatbots Life·Aug 18, 2019NLU: impact of using stemmerIntroduction When developing an NLU one of the big decissions is how to implement the tokenizer and the stemmer. The tokenizer defines how to split sentences into words. The problem is that exists different approachs to do it. …Machine Learning6 min read
Published in Chatbots Life·Jul 28, 2019Guessing how Microsoft LUIS works: some technical findingsIntroduction Usually we use the Conversational AIs for building chatbots as black-boxes, without knowing how they work inside. …NLP9 min read
Published in Planeta Chatbot : todo sobre los Chat bots, Voice apps e Inteligencia Artificial·Jul 27, 2019Benchmark de IAs ConversacionalesIntroducción A la hora de hacer un bot una de las decisiones más importantes es qué inteligencia artificial conversacional utilizar, y para ello hay que evaluar cómo se comportan. Para ello, actualmente, uno de los papers más relevantes es el SIGDIAL22 que propone 3 corpus (conjuntos de datos) para probarlas. El…NLP4 min read
Published in Chatbots Life·Jul 27, 2019Benchmarking Conversational AIsIntroduction When starting the development of a chatbot, one of the critical decissions is to choose the conversational artificial intelligence to use, and to take that decission we have to evaluate how they behave. One of the most relevant papers around this topic is SIGDIAL22 that propose 3 corpus (sets of…Bots5 min read
Mar 6, 2019How to build your own NLP for chatbotsIntroduction When building a chatbot, one of the most important parts is the NLP (Natural Language Processing), that allows us to understand what the user wants and match it into an intent (action) of our chatbot. This part that is really important, usually becomes a “black box” provided by a third…Machine Learning9 min read
Published in Planeta Chatbot : todo sobre los Chat bots, Voice apps e Inteligencia Artificial·Mar 5, 2019Cómo desarrollar tu propio NLP para Chatbots (II): Rompiendo los recordsViene de Cómo desarrollar tu propio NLP para Chatbots (I). Introducción En el artículo anterior veíamos cómo con poco código se podía llegar a un NLP tan bueno o mejor que los comerciales, basándonos en el paper SIGDIAL22, que evalúa con tres corpus muy diferentes entre ellos. …NLP4 min read
Published in Planeta Chatbot : todo sobre los Chat bots, Voice apps e Inteligencia Artificial·Mar 4, 2019Cómo desarrollar tu propio NLP para Chatbots (I)TL; DR: En tan solo 23 líneas de código se puede construir, en javascript, un sistema NLP para detectar el intent de una frase utilizando un stemmer de la librería Natural, y la librería brain.js para la red neuronal. …Chatbots10 min read
