Identify Location Entities Accurately in Chatbots

DZone 's Guide to

Identify Location Entities Accurately in Chatbots

Let's take a look at a brief article that explains how to identify location entities accurately in chatbots.

· AI Zone ·
Free Resource

When a user converses with a travel bot for booking his/her journey (maybe flight/train/bus), the bot identifies the source and destination precisely if the user query mentions the source location as the former and the destination location as the latter.

For instance, if the user enters a query like, "Book me a flight from Chennai to Bangalore." Here, the bot identifies the locations accurately. Chennai is identified as the source location since the location occurs first in the user query, and Bangalore is identified as the destination since it is the second location entity in the query.

Image title

However, if a user enters a query like, “Book me a flight to Bangalore from Chennai,” it fails to identify the right source and destination since the bot considers the first occurrence of location as the source and interprets Bangalore as the source location instead of the “destination” and Chennai as the destination location instead of the “source.”

Image title

The above concern can be handled by building a custom model. The model has to be trained with sample documents to identify the right source and destination locations using Watson Knowledge Studio(WKS), which can then be deployed to Natural Language Understanding(NLU) and integrated with the chatbot using Watson Assistant and IBM Cloud Functions. Read the detailed solution to this problem statement here.Image title

chatbot ,watson assistant ,tutorial ,artificial intelligence ,machine learning

Published at DZone with permission of

Opinions expressed by DZone contributors are their own.

{{ parent.title || parent.header.title}}

{{ parent.tldr }}

{{ parent.urlSource.name }}