Archive: Machine learning developer needed for creating a topic model

Budget 320$ per month

Posted: 5 years ago

Closed

Description: We want to build a solution that is able to take in a body of text or images with text using OCR and use (supervised) topic modeling to output the appropriate topic based on predefined “tags”/topics we feed the model. We can use APIs/available frameworks such as Tensorflow as needed (does not need to be built from the ground up).

To give an example, let’s say that the predefined tags we’ve defined were: “book, car, ball, and computer.”

If our input is a block of text such as: “Some texts are prototypically compositions of such great length that it takes a considerable investment of time to compose and a still considerable wtime to read.”

The output should be the tag, “book.”

Our use case is taking in texts/pictures of documents of building maintenance projects as inputs and determining which of our 300-500 categories the text should be matched with.

For instance, the input may be a paragraph of text that outlines a roof that needs to be repaired. Then our model should be able to determine that this belongs in our roof repair category
Skills:
machine learning,application programming interface (API),framework,general programming,software development