Back to results
US 2014/0278409 A1Published application
Preserving privacy in natural langauge databases
AssigneeAT&T Intellectual Property II, L.P.
InventorsDilek Z. Hakkani-Tur, Yucel Saygin, Min Tang, Gokhan Tur
Life of this patent
Estimating the term…
Abstract
An apparatus and a method for preserving privacy in natural language databases are provided. Natural language input may be received. At least one of sanitizing or anonymizing the natural language input may be performed to form a clean output. The clean output may be stored.
Claims20
A method comprising:
- sanitizing sensitive information found in a transcription from a speaker, to yield a clean transcription comprising sanitized text and non-sanitized text;
- and
- anonymizing the non-sanitized text by modifying a feature vector associated with the non-sanitized text, to yield a modified feature vector, such that the modified feature vector is associated with a mean feature vector of a plurality of speakers.
A system comprising:
- a processor;
- and
- a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
- sanitizing sensitive information found in a transcription from a speaker, to yield a clean transcription comprising sanitized text and non-sanitized text;
- and
- anonymizing the non-sanitized text by modifying a feature vector associated with the non-sanitized text, to yield a modified feature vector, such that the modified feature vector is associated with a mean feature vector of a plurality of speakers.
3 more elements
A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:
- sanitizing sensitive information found in a transcription from a speaker, to yield a clean transcription comprising sanitized text and non-sanitized text;
- and
- anonymizing the non-sanitized text by modifying a feature vector associated with the non-sanitized text, to yield a modified feature vector, such that the modified feature vector is associated with a mean feature vector of a plurality of speakers.
Dependencies are inferred from the claim text.