Patent · US Active

Contextual text generation for question answering and text summarization with supervised representation disentanglement and mutual information minimization

US11887008B2 · kind B2 · utility

0Cited by
1References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 8, 2020
Grant dateJan 30, 2024
Priority date
Expiry dateMay 23, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/082
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods and systems for disentangled data generation include accessing a dataset including pairs, each formed from a given input text structure and a given style label for the input text structures. An encoder is trained to disentangle a sequential text input into disentangled representations, including a content embedding and a style embedding, based on a subset of the dataset, using an objective function that includes a regularization term that minimizes mutual information between the content embedding and the style embedding. A generator is trained to generate a text output that includes content from the style embedding, expressed in a style other than that represented by the style embedding of the text input.

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