Back to results
US 2014/0236577 A1Published application
Semantic Representations of Rare Words in a Neural Probabilistic Language Model
AssigneeNEC Laboratories America, Inc.
InventorsChristopher Malon, Bing Bai
Life of this patent
Estimating the term…
Abstract
Systems and methods are disclosed for representing a word by extracting n-dimensions for the word from an original language model; if the word has been previously processed, use values previously chosen to define an (n+m) dimensional vector and otherwise randomly selecting m values to define the (n+m) dimensional vector; and applying the (n+m) dimensional vector to represent words that are not well-represented in the language model.
Claims20
A method for representing a word, comprising:
- extracting n-dimensions for the word from an original language model;
- and
- if the word has been previously processed, use values previously chosen to define an (n+m) dimensional vector and otherwise randomly selecting m values to define the (n+m) dimensional vector.
A natural language system, comprising:
- a processor to receive text and to represent a word;
- computer code to extract n-dimensions for the word from an original language model;
- and
- computer code to determine if the word has been previously processed, use values previously chosen to define an (n+m) dimensional vector and otherwise randomly selecting m values to define the (n+m) dimensional vector.
1 more element
Dependencies are inferred from the claim text.