text-to-topic-tokens

ai-research-agent / tokenize/text-to-topic-tokens

Other

Token

Properties

term

term: string;

The actual term or phrase

termCategory

termCategory: number;

The category of the term

uniqueness

uniqueness: number;

The uniqueness score of the term

Topics

convertTextToTokens()

function convertTextToTokens(phrase, options?): object[]

Convert Text Query to Topic Phrase Tokens

Returns a list of phrases that are found in Wiki Titles/ dictionary phrases World Model that match the input phrase, or just the single word if found. Search results will be more accurate if we infer likely phrases and search for those words occuring together and not just split into words and find frequency. Examples are "white house" or "state of the art" which should be searched as a phrase but would return different context if split into words. As Led Zeppelin famously put it: ♫ "'Cause you know sometimes words have two meanings."

Parameters

Parameter	Type	Description
phrase	string
options?	{ checkRootWords: number; checkTypos: number; ignoreStopWords: number; phrasesModel: Object; typosModel: Object; }
options.checkRootWords?	number	check for word's root stem
options.checkTypos?	number	check for typos
options.ignoreStopWords?	number	ignore 300+ overused words
options.phrasesModel?	Object	remote model
options.typosModel?	Object	remote model

Returns

object[]

Example

const result = convertTextToTokens("The president of the united states is in the white house", { phrasesModel, typosModel });
  console.log(result);

Author

ai-research-agent (2024)