| CPC G06F 40/30 (2020.01) | 23 Claims |

|
1. A method for processing a natural language communication in a data processing system including a processor, the method comprising:
receiving a natural language communication including an ordered sequence of a plurality of word spellings of a natural human language;
parsing, by the processor, the plurality of word spellings of the natural language communication utilizing constraint-based parsing to identify a plurality of satisfied parsing constraints, wherein the constraint-based parsing includes:
determining respective parts-of-speech of the plurality of word spellings as a result of the identification of the plurality of satisfied parsing constraints, wherein each of the parts-of-speech is a respective one of a plurality of different categories of words differentiated by different syntactic function; and
recording, in a metadata data structure for the natural language communication, the determined parts-of-speech of the plurality of word spellings in the natural language communication;
the processor performing a semantic analysis of the natural language communication based on the parts-of-speech of the plurality of word spellings as determined by the parsing, wherein performing the semantic analysis includes:
obtaining at least mid-level comprehension of the natural language communication by identifying in the natural language communication utilizing constraints at least one of the following set of elements: a clausal structure within the natural language communication, a sentence structure of a sentence in the natural language communication, an implied topic of the natural language communication, and a classical linguistic role in the natural language communication; and
recording, in a metadata data structure for the natural language communication, said at least one identified element.
|