# US 9,436,759 B2 · Robust information extraction from utterances > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 9,436,759 B2 - Document ID: US9436759B2 - Status: Granted - Kind: B2 - Application number: 14/077,214 - Filed: 2013-11-12 - Published: 2015-05-14 - Granted: 2016-09-06 - Earliest claimed: 2007-12-27 - Assignees: Nant Holdings IP, LLC - Applicants: Nant Holdings IP, LLC - Inventors: Jun Huang; Yookyung Kim; Youssef Billawala; Farzad Ehsani; Demitrios Master - Web page: https://patentgrep.com/patent/US9436759B2 ## CPC - G06F 16/3329: Natural language query formulation - G06F 16/36: Creation of semantic tools, e.g. ontology or thesauri - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract The performance of traditional speech recognition systems (as applied to information extraction or translation) decreases significantly with, larger domain size, scarce training data as well as under noisy environmental conditions. This invention mitigates these problems through the introduction of a novel predictive feature extraction method which combines linguistic and statistical information for representation of information embedded in a noisy source language. The predictive features are combined with text classifiers to map the noisy text to one of the semantically or functionally similar groups. The features used by the classifier can be syntactic, semantic, and statistical. ## Claims ### Claim 1 A classification system comprising: a non-transitory storage medium; a classification engine comprising a set of executable instructions stored on the non-transitory storage medium and configured to: receive an input associated with semantic information; generate an action-based concept tagged document of the input; classify the input into one or more semantic classes based at least in part on the action-based concept tagged document; predict paraphrased representations of the input with respect to a source language based on the one or more semantic classes; and generate a system response based on the paraphrased representations. ### Claim 2 (depends on 1) The classification system of claim 1, wherein the input comprises at least one of a speech utterance, and a text string. ### Claim 3 (depends on 1) The classification system of claim 1, wherein the classification engine is further configured to classify the input into one or more semantic classes based at least in part on at least one of feature sets and classification models. ### Claim 4 (depends on 3) The classification system of claim 3, wherein the classification engine is further configured to extract and combine at least one of statistical features, syntactic features, and semantic features from a training corpus to generate the feature sets. ### Claim 5 (depends on 3) The classification system of claim 3, wherein the classification engine is further configured to generate the classification models as a function of extracted features of a training corpus. ### Claim 6 (depends on 5) The classification system of claim 5, wherein the classification engine is further configured to balance the training corpus before generating the feature sets. ### Claim 7 (depends on 1) The classification system of claim 1, wherein the classification engine is further configured to extract feature sets from the input. ### Claim 8 (depends on 7) The classification system of claim 7, wherein the classification engine is further configured to classify the input into one or more semantic classes based at least in part on the feature sets. ### Claim 9 (depends on 7) The classification system of claim 7, wherein the classification engine is further configured to weigh features in the feature sets according to an information metric model from a training corpus. ### Claim 10 (depends on 1) The classification system of claim 1, wherein the classification engine is further configured to classify the input into one or more semantic classes according to a hierarchy. ### Claim 11 (depends on 10) The classification system of claim 10, wherein the hierarchy is based on clustering of the semantic classes. ### Claim 12 (depends on 10) The classification system of claim 10, wherein the classification engine is further configured to classify the input into one or more semantic classes by performing a top-down classification of the one or more semantic classes according to the hierarchy. ### Claim 13 (depends on 1) The classification system of claim 1, wherein the classification engine is further configured to classify the input into one or more semantic classes by refining classification of the one or more semantic classes via rule-base template matching. ### Claim 14 (depends on 1) The classification system of claim 1, wherein the classification engine is further configured to classify the input into one or more semantic classes by rejecting out-of-domain inputs based on a rejection model. ### Claim 15 (depends on 1) The classification system of claim 1, wherein the classification engine is further configured to translate the classified input based on the one or more semantic classes. ### Claim 16 (depends on 1) The classification system of claim 1, further comprising a speech recognition engine configured to generate a word recognition lattice from a speech utterance. ### Claim 17 (depends on 16) The classification system of claim 16, wherein the input received by the classification engine comprises the word recognition lattice. ### Claim 18 (depends on 1) The classification system of claim 1, wherein the system response comprises a command with respect to a task. ### Claim 19 (depends on 12) The classification system of claim 12, wherein the task relates to control behavior of an IVR system. ### Claim 20 (depends on 1) The classification system of claim 1, wherein the system response comprises a system action. ### Claim 21 (depends on 1) The classification system of claim 1, wherein the input comprises a noisy language. ### Claim 22 (depends on 1) The classification system of claim 1, wherein the input comprises an input query. ### Claim 23 (depends on 22) The classification system of claim 22, wherein the system response comprises a rejection of the input query. ### Claim 24 (depends on 22) The classification system of claim 22, wherein the system response comprises a prompt to a user. ### Claim 25 (depends on 24) The classification system of claim 24, wherein the prompt to the user comprises a request for the user to rephrase the input query. ### Claim 26 (depends on 1) The classification system of claim 1, wherein the system response relates to travel. ### Claim 27 (depends on 1) The classification system of claim 1, wherein the system response relates to a purchase. ### Claim 28 (depends on 1) The classification system of claim 1, wherein the system response relates to security. ### Claim 29 (depends on 1) The classification system of claim 1, wherein the system response relates to billing.