Common problems to face while developing a chatbot:

Negation

Many bots don’t understand negation in a phrase because they have been built based on a keyword approach. That makes it difficult for users to ask for something as simple as “I want a barbeque pizza with no pork”.  Let's see some examples:

  • “I want a barbeque pizza with no pork” (only negates pork).
  • “We don’t want any drinks” (negates the whole event).
  • “I’m not sure… I’ll take a beer (It doesn’t negate the main event)”

Double intent

Most chatbot frameworks are based around the concept of intent and entity detection, which involves identifying both the intent of an utterance and the entities relevant to that intent. For example, for the sentence “I want a pepperoni pizza”, most chatbot frameworks – after being properly configured and trained – would detect “order food” as the intent, and “pepperoni pizza” as the “food type” entity.

For simple utterances like the previous example, most chatbot frameworks work correctly. But when users ask for assistance with more complex requests, existing solutions are often not able to cope. Let's take “I want a pepperoni pizza and a soda”, which has two entities “pepperoni pizza” and “soda” which could be the object of the intent. Most frameworks only support a single entity for each intent, so they cannot easily handle natural requests with two intents such as this one. The problem is known as “double intent”. 

How can Bitext
solve the problem?

Bitext speeds up the development of multilingual bots in different ways. One example is normalizing user requests to a form that is easier to understand for the chatbot. For example, a user request like "I'd like a Hawaiian and a beer, please" will be normalized to two requests: "I want a Hawaiian pizza" and "I want a beer".

Our platform will allow you to transform any complex order into simple ones and extract an accurate JSON output ready to use in any chatbot development platform. And since we know how important multilingualism is, we offer this service in more than 20 languages.

Using our platform as middleware in your chatbot pipeline reduces up to 60% the hand-tagged data needs of any development platform. Our platform reduces the number of linguistic structures required by your bot to understand and accurately answer users.

Contact us with what you have in mind for your product and we will help you define your text analysis needs.

Test-drive our Text Analytics tools!

Our cloud services help market research professionals and data scientists perform sentiment analysis, categorization, and entity & concept extraction, easily and effectively.

Free trial. No credit card required. No obligation.

Start Analyzing

madrid

MADRID, SPAIN

José Echegaray 8 , building 3, office 4
Parque Empresarial Las Rozas
28232 Las Rozas

san-francisco

SAN FRANCISCO, USA

1700 Montgomery Street, Suite 101
CA 94111