Patent · US Active

Learning word embedding using morphological knowledge

US10606946B2 · kind B2 · utility

7Cited by
5References
10Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 4, 2015
Grant dateMar 31, 2020
Priority date
Expiry dateNov 30, 2038

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/08
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

In some examples, a machine learning system may use morphological knowledge to enhance a deep learning framework for learning word embedding. The system may consider, among other things, morphological similarities between and among words in a learning process so as to handle new or rare words, edit distances, longest common substring similarities, morpheme similarities, and syllable similarities as morphological knowledge to build a relation matrix between or among words. The system may apply the deep learning framework to query classification, web search, text mining, information retrieval, and natural language processing tasks, for example. The system may accomplish such tasks with relatively high efficiency and speed, while utilizing less computing resources as compared to other systems.

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