Hybrid learning system for natural language understanding

A method of operating a natural language understanding (NLU) framework, comprising:

• (A) generating an annotated utterance tree of an utterance using a combination of rules-based and machine-learning (ML)-based components of the NLU framework, wherein a structure of the annotated utterance tree represents a grammatical structure of the utterance, and wherein nodes of the annotated utterance tree include word vectors that represent semantic meanings of words or phrases of the utterance;
• and then
• (B) performing rule-based error detection of the annotated utterance tree;
• and
• (C) in response to at least one error being detected in Step B, performing a rule-based modification of the utterance and then returning to Step A;
• and
• (D) in response to no errors being detected in Step B, using the annotated utterance tree as a basis for intent/entity extraction of the utterance.

A non-transitory, computer-readable medium storing instructions of a natural language understanding (NLU) framework executable by one or more processors of a computing system, the instructions comprising:

• instructions to use a prosody subsystem of the NLU framework to analyze an utterance for prosody cues to segment the utterance;
• instructions to use a structure subsystem of the NLU framework to analyze the segmented utterance to generate an annotated utterance tree having nodes representing words or phrases of the utterance that are annotated with class information;
• instructions to use a vocabulary subsystem of the NLU framework to analyze the utterance to produce word vectors for the nodes of the annotated utterance tree representing the words or phrases of the utterance;
• and
• instructions to use the annotated utterance tree as a basis for intent/entity extraction of the utterance.