Text processing using natural language understanding
AssigneeNuance Communications, Inc.
InventorsSara H. Basson, Rick Hamilton, Dan Ning Jiang, Dimitri Kanevsky, David Nahamoo, Michael Picheny, Bhuvana Ramabhadran, Tara N. Sainath
Life of this patent
Estimating the term…
Abstract
Techniques for converting spoken speech into written speech are provided. The techniques include transcribing input speech via speech recognition, mapping each spoken utterance from input speech into a corresponding formal utterance, and mapping each formal utterance into a stylistically formatted written utterance.
Claims20
A method for rephrasing one or more portions of text in a first text to obtain a second text, wherein the method comprises acts of:
- using at least one processor to perform natural language understanding (NLU) processing on the first text to obtain at least one semantic representation of the first text;
- using the at least one semantic representation of the first text to generate at least one formal representation of the first text;
- analyzing the at least one formal representation of the first text to identify at least one language characteristic that is present in the first text;
- identifying a transformation rule associated with the at least one language characteristic;
- and
- obtaining the second text at least in part by applying the transformation rule associated with the at least one language characteristic to rephrase one or more portions of text in the first text.
14-19. (canceled)
A computer program product comprising a tangible computer readable recordable storage medium including computer usable program code for rephrasing one or more portions of text in a first text to obtain a second text, the computer program product including:
- computer usable program code for performing natural language understanding (NLU) processing on the first text to obtain at least one semantic representation of the first text;
- computer usable program code for using the at least one semantic representation of the first text to generate at least one formal representation of the first text;
- and
- computer usable program code for analyzing the at least one formal representation of the first text to identify at least one language characteristic that is present in the first text, identifying a transformation rule associated with the at least one language characteristic, and obtaining the second text at least in part by applying the transformation rule associated with the at least one language characteristic to rephrase one or more portions of text in the first text.
A system for rephrasing one or more portions of text in a first text to obtain a second text, comprising:
- a memory;
- and
- at least one processor coupled to the memory and operative to:
- perform natural language understanding (NLU) processing on the first text to obtain at least one semantic representation of the first text;
- use the at least one semantic representation of the first text to generate at least one formal representation of the first text;
- analyze the at least one formal representation of the first text to identify at least one language characteristic that is present in the first text;
- identify a transformation rule associated with the at least one language characteristic;
- and
- obtain the second text at least in part by applying the transformation rule associated with the at least one language characteristic to rephrase one or more portions of text in the first text.
Dependencies are inferred from the claim text.