Misspeak resolution in natural language understanding for a man-machine interface

Patent metadata

Field	Value
Publication number	US-2018268813-A1
Application number	US-201715462428-A
Country	US
Kind code	A1
Filing date	Mar 17, 2017
Priority date	Mar 17, 2017
Publication date	Sep 20, 2018
Grant date	—

Abstract

Misspeaking is resolved in a natural language understanding system to interface with a machine. In one example, a user speech utterance is received. A sequence of classifiers is applied to words of the utterance to determine a meaning of the utterance. The meaning in interpreted as a command and the command is applied to a device for execution. The classifiers may include a first classifier to determine an intended function that is a subject of the utterance, a second classifier to determine words with properties that are related to the intended function, and a third classifier to select a property to apply to the function.

First claim

What is claimed is:

1 . A method comprising:
receiving a user speech utterance; applying a sequence of classifiers to words of the utterance to determine a meaning of the utterance; interpreting the determined meaning as a command; and applying the command to a device for execution.

2 . The method of claim 1 , wherein applying a sequence of classifiers comprises applying a first classifier to determine an intended function that is a subject of the utterance and then applying a second classifier to determine words with properties that are related to the intended function.

3 . The method of claim 2 , further comprising choosing a word to apply to the intended function by applying a neural network to the words with properties that are related to the function to choose a word.

4 . The method of claim 3 , wherein the words with properties are structured as a bag of words with sequence information.

5 . The method of claim 4 , wherein bag of words features are presented as vector representatives of word collections.

6 . The method of claim 2 , further comprising selecting a function and application using the intended function.

7 . The method of claim 1 , wherein the sequence of classifiers comprise a user intent detection, followed by a word property detection, followed by a property selection made by applying the intent to words having appropriate properties.

8 . The method of claim 7 , wherein the intent detection classifier determines an intent of the user by applying probabilities of possible intents to a bag-of-words representation of the utterance and selecting a most probable intent.

9 . The method of claim 7 , wherein the word property detection classifier associates words of the utterance with properties represented by the words.

10 . The method of claim 9 , wherein the word property detection classifier detects word properties using a vocabulary and a neural network.

11 . The method of claim 9 , wherein the word property detection classifier validates each detected property against a natural language understanding module to ensure that the corresponding word can be evaluated based on the property.

12 . The method of claim 1 , further comprising the classifiers of the sequence of classifiers using data driven machine learning.

13 . The method of claim 1 , further comprising using temporal features of the words to distinguish between properties and then revising properties in the utterance.

14 . The method of claim 1 , wherein applying a sequence of classifier comprises classifying at least a portion of the words, the method further comprising applying a pre-defined rule to words of the same classification.

15 . The method of claim 1 , wherein the pre-defined rule is to use the last word of the same classification as the meaning.

16 . An apparatus comprising:
an automatic speech recognition module to receive a user speech utterance and determine a sequence of words; a natural language understanding module to apply a sequence of classifiers to the words of the utterance to determine a meaning of the utterance; and an application module to interpret the meaning as a command and to apply the command to a device for execution.

17 . The apparatus of claim 17 , wherein the natural language understanding module comprises a neural network to determine properties of words of the utterance.

18 . The apparatus of claim 17 , wherein the natural language understanding module classifier associates words of the utterance with properties represented by the words using temporal features of the words to distinguish between properties.

19 . A speech operated system comprising:
a microphone to receive a speech utterance from a user; an automatic speech recognition module to receive the speech utterance and determine a sequence of words; a natural language understanding module to apply a sequence of classifiers to the words of the utterance to determine a meaning of the utterance; an application module to interpret the meaning as a command; and an actuator to execute the command.

20 . The system of claim 19 , wherein the sequence of classifiers comprise:
a first classifier to determine an intended function that is a subject of the utterance; a second classifier to determine words with properties that are related to the intended function; and a third classifier to select a property to apply to the function.

Assignees

• Intel Ip Corp

Inventors

• Georges Munir Nikolai Alexander
• Stemmer Georg
• Jessa Szymon

Classifications

• G10L15/1822 Primary

  Parsing for meaning understanding · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L15/063

  Training · CPC title

• G10L15/1815

  Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning · CPC title

• G10L15/16

  using artificial neural networks · CPC title