Improving Rasa's results by 30% with artificial training data: Part II

[fa icon="calendar'] Jun 5, 2018 5:23:25 PM / by Bitext posted in NLU, RASA

[fa icon="comment"] 0 Comments

Bot accuracy can now be increased, easily. How? Increasing training data, not by hand, but using automatically-generated query variations. We have benchmarked Rasa and other platforms and accuracy goes up to 93% with Bitext artificial training data tech.

Read More [fa icon="long-arrow-right"]

Google I/O: Multiple Actions or Double Intent?

[fa icon="calendar'] May 24, 2018 5:40:07 PM / by Leticia Martín-Fuertes posted in Deep Linguistic Analysis, NLU

[fa icon="comment"] 0 Comments

In the past weeks a lot has been said about last Google I/O's presentation of Duplex, an assistant powered by AI that can make phone calls and talk to humans to make arrangements for you. Some people are so impressed by the achievement that they are already pointing out the ethical consequences of not being able to tell apart a human from a machine, and some are playing it down, highlighting that we have only seen a demo.

Read More [fa icon="long-arrow-right"]

Building bots? You can now stop fearing day 1 of production

[fa icon="calendar'] Apr 30, 2018 5:44:39 PM / by Leticia Martín-Fuertes posted in NLP, Chatbots, NLU

[fa icon="comment"] 0 Comments

What happens after you build a chatbot for a client? I mean, when the architecture is set up, the NLU module has been built, the conversation flows are designed, and everything is ready. All is left is going into production, where you will have thousands of users' interactions that will train your bot and make it super smart, right?

Read More [fa icon="long-arrow-right"]

Make your bot as smart as TechCrunch's

[fa icon="calendar'] Mar 15, 2018 7:41:44 PM / by Leticia Martín-Fuertes posted in NLP, Chatbots, NLG, TechCrunch, NLU, Query Rewriting

[fa icon="comment"] 0 Comments

We have already talked a lot in this blog about training chatbots, the issues bot builders encounter in this task and our tips to enhance its performance, no matter the NLU platform they are built on. DialogflowLexLUIS, we have studied them all.

Read More [fa icon="long-arrow-right"]

How we made TechCrunch's bot more conversational

[fa icon="calendar'] Mar 14, 2018 6:22:05 PM / by Leticia Martín-Fuertes posted in NLP, Chatbots, TechCrunch, NLU, Query Rewriting

[fa icon="comment"] 0 Comments

Some of you have asked for more details about the TechCrunch's Messenger bot upgrade, so we decided to share them here. Thus, in this article we will disclosure what exactly did the improvement consist on, along with some query examples and how this evolution to a more conversational bot was possible.

Read More [fa icon="long-arrow-right"]

Subscribe to Email Updates