METHOD AND SYSTEM FOR USING A STATISTICAL LANGUAGE MODEL AND AN ACTION CLASSIFIER IN PARALLEL WITH GRAMMAR FOR BETTER HANDLING OF OUT-OF-GRAMMAR UTTERANCES

• US 20080270135A1
• Filed: 04/30/2007
• Published: 10/30/2008
• Est. Priority Date: 04/30/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Jan, Ea-Ee, Visweswariah, Karthik, Goel, Vaibhava, Gopinath, Ramesh
• Granted Patent: US 8,396,713 B2
• Time in Patent Office: Days
• US Class Current: 704/257
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks
• CPC Class Codes: G10L 15/197 Probabilistic grammars, e.g. word n-grams

Abstract

A method (and system) of handling out-of-grammar utterances includes building a statistical language model for a dialog state using, generating sentences and semantic interpretations for the sentences using finite state grammar, building a statistical action classifier, receiving user input, carrying out recognition with the finite state grammar, carrying out recognition with the statistical language model, using the statistical action classifier to find semantic interpretations, comparing an output from the finite state grammar and an output from the statistical language model, deciding which output of the output from the finite state grammar and the output from the statistical language model to keep as a final recognition output, selecting the final recognition output, and outputting the final recognition result, wherein the statistical action classifier, the finite state grammar and the statistical language model are used in conjunction to carry out speech recognition and interpretation.

Claims

1. A method of handling out-of-grammar utterances, comprising:

building a statistical language model for a dialog state using data that is collected when users interact with the dialog state;

generating sentences and semantic interpretations for the sentences using finite state grammar;

building a statistical action classifier using the data set containing sentences and the associated semantic interpretations;

receiving user input;

carrying out recognition with said finite state grammar;

carrying out recognition with said statistical language model;

using said statistical action classifier to find semantic interpretations;

comparing an output from said finite state grammar and an output from said statistical language model;

deciding which output of said output from said finite state grammar and said output from said statistical language model to keep as a final recognition output;

selecting said final recognition output; and

outputting said final recognition result,

wherein said statistical action classifier, said finite state grammar and said statistical language model are used in conjunction to carry out speech recognition and interpretation.

2. The method according to claim 1, further comprising conducting a first recognition pass and a second recognition pass on each utterance in said user input.

3. The method according to claim 1, wherein if said output from said finite state grammar is greater than said output from said statistical language model, then said output from said finite state grammar is selected, and

wherein if said output from said statistical language model is greater than said output from said finite state grammar, then said output from said statistical language model is selected.