Back to results
US 8,046,355 B2Granted
Word decompounder
AssigneeGoogle Inc.
InventorsEnrique Alfonseca, Stefan H. Pharies
Life of this patent
Estimating the term…
Abstract
A word is split into one or more first substrings. A morpheme is applied to the one or more first substrings to create one or more second substrings. The one or more first and second substrings are selected as one or more splittings, and a score is generated for each of the one or more splittings. One of the one or more splittings with a score higher than the other one or more splittings is selected as a keyword.
Claims42
A method, comprising:
- identifying a first substring of a word;
- generating a set of one or more alternate substrings comprising:
- adding a morpheme to the first substring to generate an alternate substring;
- determining whether the first substring or alternate substrings appear in a query log;
- generating a score for the each respective substring based on a number of appearances of each respective substring in the query log and one or more properties associated with each respective substring;
- and
- selecting the first substring or an alternate substring as a keyword based on the score.
4 more elements
A method, comprising:
- identifying one or more first substrings of a word;
- adding a first morpheme to the one or more first substrings to create one or more second substrings;
- removing a second morpheme from the one or more first substrings to create one or more third substrings;
- selecting one or more of the one or more first, second, and third substrings as one or more splittings of the word;
- determining whether the one or more first, second, or third substrings appear in a query log;
- generating a score for each of the one or more splittings based on a determination that the one or more first, second, or third substrings appear in the query log and one or more properties associated with each of the one or more first, second, and third substrings that are selected as part of each of the one or more splittings;
- and
- selecting a splitting selected from among the one or more splittings with a score higher than the other one or more splittings as a keyword.
5 more elements
A method, comprising:
- splitting a word into one or more first substrings;
- generating a set of alternate substrings comprising:
- adding a morpheme to the one or more first substrings to generate one or more alternate substrings;
- determining whether the one or more first substrings or alternate substrings appear in a query log;
- selecting one or more of the one or more first substrings and alternate substrings as one or more splittings of the word;
- generating a score for each of the one or more splittings based on a number of appearances of the one or more first substrings and alternate substrings in the query log and one or more properties associated with each of the one or more first substrings and alternate substrings;
- and
- selecting a splitting selected from among the one or more splittings based on the score.
5 more elements
A system, comprising one or more computers, the one or more computers implementing:
- a splitting engine that splits a word into one or more first substrings, generates a set of one or more alternate substrings by adding a morpheme to the one or more first substrings, determines whether the one or more first substrings or alternate substrings appear in a query log, and selects one or more of the one or more first substrings and alternate substrings as one or more splittings of the word;
- and
- a scoring engine that generates a score for each of the one or more splittings based on a number of appearances of the one or more first substrings or alternate substrings in the query log and one or more properties associated with each of the one or more first substrings or alternate substrings, and selects a splitting selected from among the one or more splittings based on the score.
A computer-readable storage device having stored thereon instructions, which, when executed by a computer, cause the computer to perform operations comprising:
- identifying a first substring of a word;
- generating a set of one or more alternate substrings comprising:
- adding a morpheme to the first substring to generate an alternate substring;
- determining whether the first substring or alternate substrings appear in a query log;
- generating a score for the each respective substring based on a number of appearances of each respective substring in the query log and one or more properties associated with each respective substring;
- and
- selecting the first substring or an alternate substring as a keyword based on the score.
4 more elements
A system comprising:
- one or more computers;
- and
- a computer-readable storage device having stored thereon instructions that, when executed by the one or more computers, cause the one or more computers to perform operations comprising:
- identifying one or more first substrings of a word;
- adding a first morpheme to the one or more first substrings to create one or more second substrings;
- removing a second morpheme from the one or more first substrings to create one or more third substrings;
- selecting one or more of the one or more first, second, and third substrings as one or more splittings of the word;
- determining whether the one or more first, second, or third substrings appear in a query log;
- generating a score for each of the one or more splittings based on a determination that the one or more first, second, or third substrings appear in the query log and one or more properties associated with each of the one or more first, second, and third substrings that are selected as part of each of the one or more splittings;
- and
- selecting a splitting selected from among the one or more splittings with a score higher than the other one or more splittings as a keyword.
8 more elements
A computer-readable storage device having stored thereon instructions, which, when executed by a computer, cause the computer to perform operations comprising:
- identifying one or more first substrings of a word;
- adding a first morpheme to the one or more first substrings to create one or more second substrings;
- removing a second morpheme from the one or more first substrings to create one or more third substrings;
- selecting one or more of the one or more first, second, and third substrings as one or more splittings of the word;
- determining whether the one or more first, second, or third substrings appear in a query log;
- generating a score for each of the one or more splittings based on a determination that the one or more first, second, or third substrings appear in the query log and one or more properties associated with each of the one or more first, second, and third substrings that are selected as part of each of the one or more splittings;
- and
- selecting a splitting selected from among the one or more splittings with a score higher than the other one or more splittings as a keyword.
5 more elements
A system comprising:
- one or more computers;
- and
- a computer-readable storage device having stored thereon instructions that, when executed by the one or more computers, cause the one or more computers to perform operations comprising:
- splitting a word into one or more first substrings;
- generating a set of alternate substrings comprising:
- adding a morpheme to the one or more first substrings to generate one or more alternate substrings;
- determining whether the one or more first substrings or alternate substrings appear in a query log;
- selecting one or more of the one or more first substrings and alternate substrings as one or more splittings of the word;
- generating a score for each of the one or more splittings based on a number of appearances of the one or more first substrings and alternate substrings in the query log and one or more properties associated with each of the one or more first substrings and alternate substrings;
- and
- selecting a splitting selected from among the one or more splittings based on the score.
8 more elements
A computer-readable storage device having stored thereon instructions, which, when executed by a computer, cause the computer to perform operations comprising:
- splitting a word into one or more first substrings;
- generating a set of alternate substrings comprising:
- adding a morpheme to the one or more first substrings to generate one or more alternate substrings;
- determining whether the one or more first substrings or alternate substrings appear in a query log;
- selecting one or more of the one or more first substrings and alternate substrings as one or more splittings of the word;
- generating a score for each of the one or more splittings based on a number of appearances of the one or more first substrings and alternate substrings in the query log and one or more properties associated with each of the one or more first substrings and alternate substrings;
- and
- selecting a splitting selected from among the one or more splittings based on the score.
5 more elements
Dependencies are inferred from the claim text.