Patent · US Active

Interpreting text classification predictions through deterministic extraction of prominent n-grams

US11462038B2 · kind B2 · utility

0Cited by
3References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJan 10, 2020
Grant dateOct 4, 2022
Priority date
Expiry dateDec 27, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V30/414
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Provided are a computer program product, system, and method for interpreting text classification predictions through deterministic extraction of prominent n-grams. A determination is made of n-gram vectors comprising word embeddings of n-grams in a document and of a document vector comprising word embeddings of the document. A label is received from the text classifier program, comprising a text classification of the document. A determination is made of a label vector comprising word embeddings of the label. The n-gram vectors, the document vector, and the label vector are used to determine n-grams that explain the text classification of the text classifier program.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.