Why NLU Is Key for Customer Support Bots

[fa icon="calendar'] Jan 29, 2019 9:13:13 AM / by Ana Moreno posted in NLU, Segmentation, NLP

[fa icon="comment"] 0 Comments

A successful virtual agent must be able to hold a natural conversation with a human. Processing natural language is, however, not a piece of cake for Artificial Intelligence. The way we speak is not regular and robotic, but emotional and full of context. NLU becomes, therefore, essential for customer support bots to get what clients need.

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

Make Your AI Solutions Global with Multilingual NLP Tools

[fa icon="calendar'] Dec 20, 2018 12:13:43 PM / by Ana Moreno posted in AI, Multilanguage, NLU

[fa icon="comment"] 0 Comments

In an era of globalization, being multilingual is essential for business. Either for your e-commerce bot to understand international customers, or for your feedback management platform to get insights from every user, English is not enough. 

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

AI Challenges Are Being Met but... Who Broke Ground Here?

[fa icon="calendar'] Dec 13, 2018 3:39:54 PM / by Ana Moreno posted in Query Rewriting, NLU, Deep Linguistic Analysis

[fa icon="comment"] 0 Comments

While AI is one of the most important trends nowadays, there are still challenges to overcome. Apart from common technical issues such as a lack of quality data, there is much  beyond its abilities for an AI to effectively understand and react when it comes to human-machine interaction.

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

How to Make Your Bot Conversational in Three Steps

[fa icon="calendar'] Nov 6, 2018 6:00:00 PM / by Ana Moreno posted in NLG, NLU, Sentiment Analysis

[fa icon="comment"] 0 Comments

Users speak the way they choose, not as you wish. Developers are building tens of bots and almost all of them bump into the same problem: they are not properly working. Most of the bots don’t understand users and the problem lies in their training. That’s the simple truth every bot developer must face sooner or later. The question is: are they facing it the right way?

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

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

Increasing bot accuracy has never been so easy. How? Generating artificial training data, not manually, but using auto-generated query variations. We have benchmarked Rasa and other platforms, and their accuracy comes up to a 93% thanks to Bitext artificial training data tech.

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

Subscribe to Email Updates