Deriving multiple meaning representations for an utterance in a natural language understanding (nlu) framework

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

• performing vocabulary injection to generate a set of utterances based on an original utterance, wherein the set of utterances includes the original utterance and one or more re-expressions of the original utterance;
• performing part-of-speech (POS) tagging of the set of utterances to generate a set of potential POS taggings for the set of utterances;
• performing variability filtering to remove POS taggings from the set of potential POS taggings that are substantially similar to other POS taggings in the set of potential POS taggings;
• parsing the set of potential POS taggings to generate a set of potential meaning representations;
• and
• calculating a respective final score for each potential meaning representation in the set of potential meaning representations and selecting a final set of meaning representations for the original utterance from the set of potential meaning representations based on the respective final score of each potential meaning representation in the set of potential meaning representations.

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:

• receive an original utterance, wherein the original utterance is a user utterance is a sample utterance of an intent-entity model;
• cleanse the original utterance by replacing or removing one or more tokens of the original utterance;
• perform vocabulary injection to generate a set of utterances from the original utterance, wherein the set of utterances includes the original utterance and one or more re-expressions of the original utterance;
• perform part-of-speech (POS) tagging of the set of utterances to generate a set of potential POS taggings for the set of utterances;
• perform variability filtering to remove POS taggings from the set of potential POS taggings that are substantially similar to other POS taggings in the set of potential POS taggings;
• parse the set of potential POS taggings to generate a set of potential meaning representations;
• calculate a respective final score for each potential meaning representation in the set of potential meaning representations and selecting a final set of meaning representations for the original utterance from the set of potential meaning representations based on the respective final score of each potential meaning representation in the set of potential meaning representations;
• and
• perform a meaning search using the final set of meaning representations, wherein the final set of meaning representations form part of an utterance meaning model that defines a search key of the meaning search or form part of an understanding model that defines a search space for the meaning search.