DETECTION MECHANISM FOR AUTOMATED DIALOG SYSTEMS
First Claim
1. A method for providing a conversational system that detects important out-of-domain content, comprising:
- receiving an utterance having multiple words;
performing a parsing operation on the utterance by parser code stored in memory and executed by a processor on a computing device;
determining one or more words of the utterance are not recognized by the parser;
determining that one or more of the one or more words not recognized by the parser are important by classifier code stored in memory and executed by a processor on the computing device; and
generating an action based on the words that are parsed by the parser and the important words that are not parsed by the parser.
2 Assignments
0 Petitions
Accused Products
Abstract
A conversational system receives an utterance, and a parser performs a parsing operation on the utterance, resulting in some words being parsed and some words not being parsed. For the words that are not parsed, words or phrases determined to be unimportant are ignored. The resulting unparsed words are processed to determine the likelihood they are important and whether they should be addressed by the automated assistant. For example, if a score associated with an important unparsed word achieves a particular threshold, then a course of action to take for the utterance may include providing a message that the portion of the utterance associated with the important unparsed word cannot be handled.
8 Citations
14 Claims
-
1. A method for providing a conversational system that detects important out-of-domain content, comprising:
-
receiving an utterance having multiple words; performing a parsing operation on the utterance by parser code stored in memory and executed by a processor on a computing device; determining one or more words of the utterance are not recognized by the parser; determining that one or more of the one or more words not recognized by the parser are important by classifier code stored in memory and executed by a processor on the computing device; and generating an action based on the words that are parsed by the parser and the important words that are not parsed by the parser. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12)
-
-
13. A system for generating annotated dialogue system training data, comprising:
-
a processor; memory; one or more modules stored in memory and executable by the processor to receive an utterance having multiple words, perform a parsing operation on the utterance by parser code stored in memory and executed by a processor on a computing device, determine one or more words of the utterance are not recognized by the parser, determine that one or more of the one or more words not recognized by the parser are important by classifier code stored in memory and executed by a processor on the computing device, and generate an action based on the words that are parsed by the parser and the important words that are not parsed by the parser.
-
-
14. A non-transitory computer readable storage medium having embodied thereon a program, the program being executable by a processor to perform a method for generating annotated dialogue system training data, the method comprising:
-
receiving an utterance having multiple words; performing a parsing operation on the utterance by parser code stored in memory and executed by a processor on a computing device; determining one or more words of the utterance are not recognized by the parser; determining that one or more of the one or more words not recognized by the parser are important by classifier code stored in memory and executed by a processor on the computing device; and generating an action based on the words that are parsed by the parser and the important words that are not parsed by the parser.
-
Specification