| CPC G06F 40/30 (2020.01) | 20 Claims |
|
1. A method, comprising:
receiving, via a processor, a dataset that includes a plurality of input texts, each input text from the plurality of input texts associated with a content category from a plurality of content categories based on a comparison between that input text and an intended meaning that is common for each comparison;
for each model in a plurality of models, running, via the processor, that model on each input text from the plurality of input texts to generate an average similarity/dissimilarity score for each content category from the plurality of content categories;
selecting, via the processor and based on the average similarity/dissimilarity score for each content category from the plurality of content categories for each model in the plurality of models, at least one model from the plurality of models to determine whether an input text is similar/dissimilar to the intended meaning; and
generating, via the processor, at least one content category-specific natural language processing pipeline associated with at least one content category included in the plurality of content categories, the average similarity/dissimilarity score for the at least one content category being outside an acceptable range.
|