Processing natural language arguments and propositions

Abstract

Natural language content can be provided by multiple and various sources. Once in text format, such content may be provided to various systems for further processing to identify one or more propositions. The relationship between each proposition may be identified and ordered according to the identified relationships. A visual display may be generated to illustrate the identified propositions and relationship, as well as identify any propositions that may be missing, unsupported, or other characteristic thereof.

1 . (canceled) 
     
     
         2 . A method of natural language processing, the method comprising:
 receiving a natural language input;   identifying relationships between portions of the natural language input;   identifying, based on the relationships, a core value conveyed by the natural language input; and   generating an output based on the core value.   
     
     
         3 . The method of  claim 2 , wherein the core value includes an intent associated with the natural language input. 
     
     
         4 . The method of  claim 3 , wherein generating the output based on the core value includes avoiding a proposition in the output based on the intent. 
     
     
         5 . The method of  claim 3 , wherein generating the output based on the core value includes seeking a proposition in the output based on the intent. 
     
     
         6 . The method of  claim 2 , wherein the core value includes an incentive associated with the natural language input. 
     
     
         7 . The method of  claim 2 , wherein the core value includes a value conflict between at least a subset of the portions of the natural language input. 
     
     
         8 . The method of  claim 2 , wherein the core value includes a value conflict between the natural language input and a second natural language input. 
     
     
         9 . The method of  claim 2 , wherein identifying the core value is based on input of the natural language input into a trained machine learning model. 
     
     
         10 . The method of  claim 9 , wherein the natural language input is associated with an agent, and wherein prior training associated with the trained machine learning model is based on prior natural language inputs from the agent and prior core values associated with the prior natural language inputs. 
     
     
         11 . The method of  claim 9 , further comprising:
 further training the trained machine learning model based on the natural language input and the core value.   
     
     
         12 . The method of  claim 2 , wherein the output includes a response to the natural language input. 
     
     
         13 . The method of  claim 2 , further comprising:
 mapping the natural language input to a vector with one or more dimensions.   
     
     
         14 . The method of  claim 2 , further comprising:
 processing the natural language input from an audio format into a text format.   
     
     
         15 . The method of  claim 2 , further comprising:
 processing the natural language input from an image-based format into a text format using optical character recognition.   
     
     
         16 . The method of  claim 2 , wherein receiving the natural language input includes receiving audio. 
     
     
         17 . The method of  claim 2 , further comprising:
 processing the output from a text format into an audio format.   
     
     
         18 . The method of  claim 2 , wherein the output identifies the core value. 
     
     
         19 . The method of  claim 2 , wherein the output is also based on the relationships between the portions of the natural language input. 
     
     
         20 . The method of  claim 2 , further comprising:
 outputting the output through a user interface, wherein receiving the natural language input includes receiving the natural language input through the user interface.   
     
     
         21 . A system for natural language processing, the system comprising:
 at least one memory; and   at least one processor, wherein execution of instructions stored in the at least one memory by the at least one processor causes the at least one processor to:
 receive a natural language input; 
 identify relationships between portions of the natural language input; 
 identify, based on the relationships, a core value conveyed by the natural language input; and 
 generate an output based on the core value.