Patent · US Active

System and method for feature-rich continuous space language models

US9092425B2 · kind B2 · utility

9Cited by
1References
17Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 8, 2010
Grant dateJul 28, 2015
Priority date
Expiry dateJul 1, 2033

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F40/40
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Disclosed herein are systems, methods, and non-transitory computer-readable storage media for predicting probabilities of words for a language model. An exemplary system configured to practice the method receives a sequence of words and external data associated with the sequence of words and maps the sequence of words to an X-dimensional vector, corresponding to a vocabulary size. Then the system processes each X-dimensional vector, based on the external data, to generate respective Y-dimensional vectors, wherein each Y-dimensional vector represents a dense continuous space, and outputs at least one next word predicted to follow the sequence of words based on the respective Y-dimensional vectors. The X-dimensional vector, which is a binary sparse representation, can be higher dimensional than the Y-dimensional vector, which is a dense continuous space. The external data can include part-of-speech tags, topic information, word similarity, word relationships, a particular topic, and succeeding parts of speech in a given history.

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