Computer-based systems utilizing textual embedding space software engines for identifying candidate phrases in a text document and methods of use thereof

A method, comprising:

• generating, by the processor, a plurality of embedding vectors in a textual embedding space by inputting a plurality of phrases in a text into an embedding engine;
• wherein each embedding vector in the plurality of embedding vectors in the textual embedding space corresponds respectively to a phrase in the plurality of phrases;
• wherein each embedding vector in the plurality of embedding vectors in the textual embedding space represents a location in the textual embedding space;
• generating, by the processor, a mapping of each embedding vector in the plurality of embedding vectors in the textual embedding space with each corresponding phrase in the plurality of phrases and a text location of each corresponding phrase in the plurality of phrases in the text;
• receiving, by the processor, an input of a candidate phrase by a user;
• generating, by the processor, a candidate embedding vector representing a candidate phrase location in the textual embedding space by inputting the candidate phrase into the embedding engine;
• computing, by the processor, a plurality of embedding space distances between the candidate phrase location and each respective location of each embedding vector in the plurality of embedding vectors in the textual embedding space;
• computing, by the processor, a plurality of similarity scores based on the plurality of embedding space distances;
• and
• outputting, by the processor, the plurality of phrases with the similarity scores to the user and the text locations in the text based on the mapping.