WordScramble

0 ×

One of your tasks at work is to train a model using sentences with the correct word context (i.e., words in a sentence following a meaningful and correct order). However, to train such model, you also need to create a dataset of words used in an incorrect context. You can think of this task as a version of Negative Sampling - a neat technique for training the famous Word2Vec model. Concretely, in this challenge you will create a workflow that takes a sentence and scrambles the order of its words. You can create a small sample of sentences to test your work with the Table Creator node.

Input
I like cats.

Output
cats. like I

Hint: Our simple solution only uses 5 nodes, but the permutations are not exactly random. Conversely, our more complex solution uses more than 15 nodes and 2 loops, as well as the Random Numbers Generator node, to create truly scrambled sentences. Bonus: Create a solution with true randomization without using any loops.

Nodes

• String Manipulation2 ×
• Bag Of Words Creator1 ×
• GroupBy1 ×
• Random Number Assigner1 ×
• Sorter1 ×
• Strings To Document1 ×
• Table Creator1 ×
• Term To String1 ×

Extensions

• FeatureKNIME Base nodes
• FeatureKNIME Data Generation
• FeatureKNIME Javasnippet
• FeatureKNIME Textprocessing

Links

• No links available