Back to results
US 2014/0279804 A1Published application
Jabba-type contextual tagger
AssigneeYahoo! Inc.
InventorJosh Coalson
Life of this patent
Estimating the term…
Abstract
Example methods, apparatuses, or articles of manufacture are disclosed that may be implemented, in whole or in part, using one or more computing devices to facilitate or otherwise support one or more processes or operations for a Jabba-type contextual tagger.
Claims20
A method comprising:
- electronically applying a tagging scheme to generate one or more labels with respect to one or more sequences of candidate atoms, said tagging scheme is applied without utilizing one or more machine-learned models, and further comprising:
- accessing one or more digital signals representative of a rule defining said one or more sequences of candidate atoms;
- and
- generating one or more digital signals representative of said one or more labels based, at least in part, on one or more slot actions having at least one slot name associated with said rule.
1 more element
An apparatus comprising:
- a computing platform comprising at least one processor to:
- electronically apply a tagging scheme to generate one or more labels with respect to one or more sequences of candidate atoms, said tagging scheme is applied without utilizing one or more machine-learned models, wherein said at least one processor further to:
- access one or more digital signals representative of a rule defining said one or more sequences of candidate atoms;
- and
- generate one or more digital signals representative of said one or more labels based, at least in part, on one or more slot actions having at least one slot name associated with said rule.
2 more elements
An article comprising:
- a non-transitory storage medium having instructions stored thereon executable by a special purpose computing platform to:
- electronically apply a tagging scheme to generate one or more labels with respect to one or more sequences of candidate atoms, said tagging scheme is applied without utilizing one or more machine-learned models, wherein said instructions further to:
- access one or more digital signals representative of a rule defining said one or more sequences of candidate atoms;
- and
- generate one or more digital signals representative of said one or more labels based, at least in part, on one or more slot actions having at least one slot name associated with said rule.
2 more elements
Dependencies are inferred from the claim text.