Multi-classification of Google-queries using a neural network in Python
It's been a long time since the publication of my first article on the topic of natural language processing. I continued to actively explore this topic, every day discovering something new.
Today I would like to talk about one of the ways to classify search queries, into separate categories using a neural network on Keras. The sphere of cars was chosen as the subject area of inquiries.
The basis was a data set of ~ 32000 search queries, classified into 14 classes: Autoinsurance, Auto Insurance, Driving License, Complaints, Entry to the State Traffic Safety Inspectorate, Record at the MADI, Medical Record, Violations and Penalties, Appeals to MADI and AMPP, Title Registration, Registration Status, Taxi, Evacuation. GITHUB . Let's get down to business, namely, run the script on the command line and begin to drive the requests:
Figure 1 - Example of using the classifier
The result is quite obvious - the classifier accurately recognizes any inquiries that we enter, which means that all the work was done in vain!
CONCLUSIONS AND CONCLUSION
The neural network coped with the task posed perfectly and this is not seen with an armed gaze. An example of practical application of this model can be considered the sphere of public services, where citizens file all kinds of applications, complaints, etc. Automating the reception of all these "pieces of paper" with the help of intellectual classification can significantly speed up the work of all state bodies.
Your suggestions for practical application, as well as opinion about the article I'm waiting for in the comments!
It may be interesting